Suchergebnis: Katalogdaten im Frühjahrssemester 2020

Cyber Security Master Information
Vertiefungsgebiet
Kernfächer
NummerTitelTypECTSUmfangDozierende
263-4660-00LApplied Cryptography Information Belegung eingeschränkt - Details anzeigen
Number of participants limited to 150.
W8 KP3V + 2U + 2PK. Paterson
KurzbeschreibungThis course will introduce the basic primitives of cryptography, using rigorous syntax and game-based security definitions. The course will show how these primitives can be combined to build cryptographic protocols and systems.
LernzielThe goal of the course is to put students' understanding of cryptography on sound foundations, to enable them to start to build well-designed cryptographic systems, and to expose them to some of the pitfalls that arise when doing so.
InhaltBasic symmetric primitives (block ciphers, modes, hash functions); generic composition; AEAD; basic secure channels; basic public key primitives (encryption,signature, DH key exchange); ECC; randomness; applications.
LiteraturTextbook: Boneh and Shoup, “A Graduate Course in Applied Cryptography”, Link.
Voraussetzungen / BesonderesIdeally, students will have taken the D-INFK Bachelors course “Information Security" or an equivalent course at Bachelors level.
Wahlfächer
NummerTitelTypECTSUmfangDozierende
252-0408-00LCryptographic Protocols Information W6 KP2V + 2U + 1AM. Hirt, U. Maurer
KurzbeschreibungThe course presents a selection of hot research topics in cryptography. The choice of topics varies and may include provable security, interactive proofs, zero-knowledge protocols, secret sharing, secure multi-party computation, e-voting, etc.
LernzielIndroduction to a very active research area with many gems and paradoxical
results. Spark interest in fundamental problems.
InhaltThe course presents a selection of hot research topics in cryptography. The choice of topics varies and may include provable security, interactive proofs, zero-knowledge protocols, secret sharing, secure multi-party computation, e-voting, etc.
Skriptthe lecture notes are in German, but they are not required as the entire
course material is documented also in other course material (in english).
Voraussetzungen / BesonderesA basic understanding of fundamental cryptographic concepts
(as taught for example in the course Information Security or
in the course Cryptography Foundations) is useful, but not required.
263-2925-00LProgram Analysis for System Security and Reliability Information W6 KP2V + 1U + 2AP. Tsankov
KurzbeschreibungSecurity issues in modern systems (blockchains, datacenters, AI) result in billions of losses due to hacks. This course introduces the security issues in modern systems and state-of-the-art automated techniques for building secure and reliable systems. The course has a practical focus and covers systems built by successful ETH spin-offs.
Lernziel* Learn about security issues in modern systems -- blockchains, smart contracts, AI-based systems (e.g., autonomous cars), data centers -- and why they are challenging to address.

* Understand how the latest automated analysis techniques work, both discrete and probabilistic.

* Understand how these techniques combine with machine-learning methods, both supervised and unsupervised.

* Understand how to use these methods to build reliable and secure modern systems.

* Learn about new open problems that if solved can lead to research and commercial impact.
InhaltPart I: Security of Blockchains

- We will cover existing blockchains (e.g., Ethereum, Bitcoin), how they work, what the core security issues are, and how these have led to massive financial losses.
- We will show how to extract useful information about smart contracts and transactions using interactive analysis frameworks for querying blockchains (e.g. Google's Ethereum BigQuery).
- We will discuss the state-of-the-art security tools (e.g., Link) for ensuring that smart contracts are free of security vulnerabilities.
- We will study the latest automated reasoning systems (e.g., Link) for checking custom (temporal) properties of smart contracts and illustrate their operation on real-world use cases.
- We will study the underlying methods for automated reasoning and testing (e.g., abstract interpretation, symbolic execution, fuzzing) are used to build such tools.


Part II: Security of Datacenters and Networks

- We will show how to ensure that datacenters and ISPs are secured using declarative reasoning methods (e.g., Datalog). We will also see how to automatically synthesize secure configurations (e.g. using SyNET and NetComplete) which lead to desirable behaviors, thus automating the job of the network operator and avoiding critical errors.
- We will discuss how to apply modern discrete probabilistic inference (e.g., PSI and Bayonet) so to reason about probabilistic network properties (e.g., the probability of a packet reaching a destination if links fail).


Part III: Machine Learning for Security

- We will discuss how machine learning models for structured prediction are used to address security tasks, including de-obfuscation of binaries (Debin: Link), Android APKs (DeGuard: Link) and JavaScript (JSNice: Link).
- We will study to leverage program abstractions in combination with clustering techniques to learn security rules for cryptography APIs from large codebases.
- We will study how to automatically learn to identify security vulnerabilities related to the handling of untrusted inputs (cross-Site scripting, SQL injection, path traversal, remote code execution) from large codebases.


To gain a deeper understanding, the course will involve a hands-on programming project where the methods studied in the class will be applied.
263-4600-00LFormal Methods for Information Security Information W5 KP2V + 1U + 1AR. Sasse, C. Sprenger
KurzbeschreibungThe course focuses on formal methods for the modelling and analysis of security protocols for critical systems, ranging from authentication protocols for network security to electronic voting protocols and online banking.
LernzielThe students will learn the key ideas and theoretical foundations of formal modelling and analysis of security protocols. The students will complement their theoretical knowledge by solving practical exercises, completing a small project, and using state-of-the-art tools.
InhaltThe course treats formal methods mainly for the modelling and analysis of security protocols. Cryptographic protocols (such as SSL/TLS, SSH, Kerberos, SAML single-sign on, and IPSec) form the basis for secure communication and business processes. Numerous attacks on published protocols show that the design of cryptographic protocols is extremely error-prone. A rigorous analysis of these protocols is therefore indispensable, and manual analysis is insufficient. The lectures cover the theoretical basis for the (tool-supported) formal modeling and analysis of such protocols. Specifically, we discuss their operational semantics, the formalization of security properties, and techniques and algorithms for their verification.

In addition to the classical security properties for confidentiality and authentication, we will study strong secrecy and privacy properties. We will discuss electronic voting protocols, and RFID protocols (a staple of the Internet of Things), where these properties are central. The accompanying tutorials provide an opportunity to apply the theory and tools to concrete protocols. Moreover, we will discuss methods to abstract and refine security protocols and the link between symbolic protocol models and cryptographic models.

Furthermore, we will also present a security notion for general systems based on non-interference as well as language-based information flow security where non-interference is enforced via a type system.
263-4656-00LDigital Signatures Information W4 KP2V + 1AD. Hofheinz
KurzbeschreibungDigital signatures as one central cryptographic building block. Different security goals and security definitions for digital signatures, followed by a variety of popular and fundamental signature schemes with their security analyses.
LernzielThe student knows a variety of techniques to construct and analyze the security of digital signature schemes. This includes modularity as a central tool of constructing secure schemes, and reductions as a central tool to proving the security of schemes.
InhaltWe will start with several definitions of security for signature schemes, and investigate the relations among them. We will proceed to generic (but inefficient) constructions of secure signatures, and then move on to a number of efficient schemes based on concrete computational hardness assumptions. On the way, we will get to know paradigms such as hash-then-sign, one-time signatures, and chameleon hashing as central tools to construct secure signatures.
LiteraturJonathan Katz, "Digital Signatures."
Voraussetzungen / BesonderesIdeally, students will have taken the D-INFK Bachelors course "Information Security" or an equivalent course at Bachelors level.
Seminar
NummerTitelTypECTSUmfangDozierende
263-4651-00LCurrent Topics in Cryptography Information Belegung eingeschränkt - Details anzeigen
Number of participants limited to 24.

The deadline for deregistering expires at the end of the second week of the semester. Students who are still registered after that date, but do not attend the seminar, will officially fail the seminar.
W2 KP2SD. Hofheinz, U. Maurer, K. Paterson
KurzbeschreibungIn this seminar course, students present and discuss a variety of recent research papers in Cryptography.
LernzielIndependent study of scientific literature and assessment of its contributions as well as learning and practicing presentation techniques.
InhaltThe course lecturers will provide a list of papers from which students will select.
LiteraturThe reading list will be published on the course website.
Voraussetzungen / BesonderesIdeally, students will have taken the D-INFK Bachelors course “Information Security" or an equivalent course at Bachelors level. Ideally, they will have attended or will attend in parallel the Masters course in "Applied Cryptography”.
Semesterprojekt
NummerTitelTypECTSUmfangDozierende
260-0100-00LSemester Project
Only for Cyber Security MSc
W12 KP26AProfessor/innen
KurzbeschreibungThe Semester Project provides students with the opportunity to apply acquired knowledge and skills.
LernzielThe students can gain hand-on experience by solving independently a technical-scientific problem.
Voraussetzungen / BesonderesPrerequisites: At least one core course in Cyber Security and one inter focus course must have been completed successfully.
Ergänzung
Computational Science
Kernfächer
NummerTitelTypECTSUmfangDozierende
401-3632-00LComputational StatisticsW8 KP3V + 1UM. H. Maathuis
KurzbeschreibungWe discuss modern statistical methods for data analysis, including methods for data exploration, prediction and inference. We pay attention to algorithmic aspects, theoretical properties and practical considerations. The class is hands-on and methods are applied using the statistical programming language R.
LernzielThe student obtains an overview of modern statistical methods for data analysis, including their algorithmic aspects and theoretical properties. The methods are applied using the statistical programming language R.
Voraussetzungen / BesonderesAt least one semester of (basic) probability and statistics.

Programming experience is helpful but not required.
Wahlfächer
NummerTitelTypECTSUmfangDozierende
252-0526-00LStatistical Learning Theory Information W7 KP3V + 2U + 1AJ. M. Buhmann, C. Cotrini Jimenez
KurzbeschreibungThe course covers advanced methods of statistical learning:

- Variational methods and optimization.
- Deterministic annealing.
- Clustering for diverse types of data.
- Model validation by information theory.
LernzielThe course surveys recent methods of statistical learning. The fundamentals of machine learning, as presented in the courses "Introduction to Machine Learning" and "Advanced Machine Learning", are expanded from the perspective of statistical learning.
Inhalt- Variational methods and optimization. We consider optimization approaches for problems where the optimizer is a probability distribution. We will discuss concepts like maximum entropy, information bottleneck, and deterministic annealing.

- Clustering. This is the problem of sorting data into groups without using training samples. We discuss alternative notions of "similarity" between data points and adequate optimization procedures.

- Model selection and validation. This refers to the question of how complex the chosen model should be. In particular, we present an information theoretic approach for model validation.

- Statistical physics models. We discuss approaches for approximately optimizing large systems, which originate in statistical physics (free energy minimization applied to spin glasses and other models). We also study sampling methods based on these models.
SkriptA draft of a script will be provided. Lecture slides will be made available.
LiteraturHastie, Tibshirani, Friedman: The Elements of Statistical Learning, Springer, 2001.

L. Devroye, L. Gyorfi, and G. Lugosi: A probabilistic theory of pattern recognition. Springer, New York, 1996
Voraussetzungen / BesonderesKnowledge of machine learning (introduction to machine learning and/or advanced machine learning)
Basic knowledge of statistics.
261-5120-00LMachine Learning for Health Care Information Belegung eingeschränkt - Details anzeigen
Number of participants limited to 150.
W5 KP3P + 1AG. Rätsch, J. Vogt, V. Boeva
KurzbeschreibungThe course will review the most relevant methods and applications of Machine Learning in Biomedicine, discuss the main challenges they present and their current technical problems.
LernzielDuring the last years, we have observed a rapid growth in the field of Machine Learning (ML), mainly due to improvements in ML algorithms, the increase of data availability and a reduction in computing costs. This growth is having a profound impact in biomedical applications, where the great variety of tasks and data types enables us to get benefit of ML algorithms in many different ways. In this course we will review the most relevant methods and applications of ML in biomedicine, discuss the main challenges they present and their current technical solutions.
InhaltThe course will consist of four topic clusters that will cover the most relevant applications of ML in Biomedicine:
1) Structured time series: Temporal time series of structured data often appear in biomedical datasets, presenting challenges as containing variables with different periodicities, being conditioned by static data, etc.
2) Medical notes: Vast amount of medical observations are stored in the form of free text, we will analyze stategies for extracting knowledge from them.
3) Medical images: Images are a fundamental piece of information in many medical disciplines. We will study how to train ML algorithms with them.
4) Genomics data: ML in genomics is still an emerging subfield, but given that genomics data are arguably the most extensive and complex datasets that can be found in biomedicine, it is expected that many relevant ML applications will arise in the near future. We will review and discuss current applications and challenges.
Voraussetzungen / BesonderesData Structures & Algorithms, Introduction to Machine Learning, Statistics/Probability, Programming in Python, Unix Command Line

Relation to Course 261-5100-00 Computational Biomedicine: This course is a continuation of the previous course with new topics related to medical data and machine learning. The format of Computational Biomedicine II will also be different. It is helpful but not essential to attend Computational Biomedicine before attending Computational Biomedicine II.
263-5300-00LGuarantees for Machine Learning Information Belegung eingeschränkt - Details anzeigen W5 KP2V + 2AF. Yang
KurzbeschreibungThis course teaches classical and recent methods in statistics and optimization commonly used to prove theoretical guarantees for machine learning algorithms. The knowledge is then applied in project work that focuses on understanding phenomena in modern machine learning.
LernzielThis course is aimed at advanced master and doctorate students who want to understand and/or conduct independent research on theory for modern machine learning. For this purpose, students will learn common mathematical techniques from statistical learning theory. In independent project work, they then apply their knowledge and go through the process of critically questioning recently published work, finding relevant research questions and learning how to effectively present research ideas to a professional audience.
InhaltThis course teaches some classical and recent methods in statistical learning theory aimed at proving theoretical guarantees for machine learning algorithms, including topics in

- concentration bounds, uniform convergence
- high-dimensional statistics (e.g. Lasso)
- prediction error bounds for non-parametric statistics (e.g. in kernel spaces)
- minimax lower bounds
- regularization via optimization

The project work focuses on active theoretical ML research that aims to understand modern phenomena in machine learning, including but not limited to

- how overparameterization could help generalization ( interpolating models, linearized NN )
- how overparameterization could help optimization ( non-convex optimization, loss landscape )
- complexity measures and approximation theoretic properties of randomly initialized and
trained NN
- generalization of robust learning ( adversarial robustness, standard and robust error tradeoff )
- prediction with calibrated confidence ( conformal prediction, calibration )
Voraussetzungen / BesonderesIt’s absolutely necessary for students to have a strong mathematical background (basic real analysis, probability theory, linear algebra) and good knowledge of core concepts in machine learning taught in courses such as “Introduction to Machine Learning”, “Regression”/ “Statistical Modelling”. It's also helpful to have heard an optimization course or approximation theoretic course. In addition to these prerequisites, this class requires a certain degree of mathematical maturity—including abstract thinking and the ability to understand and write proofs.
Distributed Systems
Kernfächer
NummerTitelTypECTSUmfangDozierende
227-0558-00LPrinciples of Distributed Computing Information W7 KP2V + 2U + 2AR. Wattenhofer, M. Ghaffari
KurzbeschreibungWe study the fundamental issues underlying the design of distributed systems: communication, coordination, fault-tolerance, locality, parallelism, self-organization, symmetry breaking, synchronization, uncertainty. We explore essential algorithmic ideas and lower bound techniques.
LernzielDistributed computing is essential in modern computing and communications systems. Examples are on the one hand large-scale networks such as the Internet, and on the other hand multiprocessors such as your new multi-core laptop. This course introduces the principles of distributed computing, emphasizing the fundamental issues underlying the design of distributed systems and networks: communication, coordination, fault-tolerance, locality, parallelism, self-organization, symmetry breaking, synchronization, uncertainty. We explore essential algorithmic ideas and lower bound techniques, basically the "pearls" of distributed computing. We will cover a fresh topic every week.
InhaltDistributed computing models and paradigms, e.g. message passing, shared memory, synchronous vs. asynchronous systems, time and message complexity, peer-to-peer systems, small-world networks, social networks, sorting networks, wireless communication, and self-organizing systems.

Distributed algorithms, e.g. leader election, coloring, covering, packing, decomposition, spanning trees, mutual exclusion, store and collect, arrow, ivy, synchronizers, diameter, all-pairs-shortest-path, wake-up, and lower bounds
SkriptAvailable. Our course script is used at dozens of other universities around the world.
LiteraturLecture Notes By Roger Wattenhofer. These lecture notes are taught at about a dozen different universities through the world.

Distributed Computing: Fundamentals, Simulations and Advanced Topics
Hagit Attiya, Jennifer Welch.
McGraw-Hill Publishing, 1998, ISBN 0-07-709352 6

Introduction to Algorithms
Thomas Cormen, Charles Leiserson, Ronald Rivest.
The MIT Press, 1998, ISBN 0-262-53091-0 oder 0-262-03141-8

Disseminatin of Information in Communication Networks
Juraj Hromkovic, Ralf Klasing, Andrzej Pelc, Peter Ruzicka, Walter Unger.
Springer-Verlag, Berlin Heidelberg, 2005, ISBN 3-540-00846-2

Introduction to Parallel Algorithms and Architectures: Arrays, Trees, Hypercubes
Frank Thomson Leighton.
Morgan Kaufmann Publishers Inc., San Francisco, CA, 1991, ISBN 1-55860-117-1

Distributed Computing: A Locality-Sensitive Approach
David Peleg.
Society for Industrial and Applied Mathematics (SIAM), 2000, ISBN 0-89871-464-8
Voraussetzungen / BesonderesCourse pre-requisites: Interest in algorithmic problems. (No particular course needed.)
263-3800-00LAdvanced Operating Systems Information W7 KP2V + 2U + 2AD. Cock, T. Roscoe
KurzbeschreibungThis course is intended to give students a thorough understanding of design and implementation issues for modern operating systems, with a particular emphasis on the challenges of modern hardware features. We will cover key design issues in implementing an operating system, such as memory management, scheduling, protection, inter-process communication, device drivers, and file systems.
LernzielThe goals of the course are, firstly, to give students:

1. A broader perspective on OS design than that provided by knowledge of Unix or Windows, building on the material in a standard undergraduate operating systems class

2. Practical experience in dealing directly with the concurrency, resource management, and abstraction problems confronting OS designers and implementers

3. A glimpse into future directions for the evolution of OS and computer hardware design
InhaltThe course is based on practical implementation work, in C and assembly language, and requires solid knowledge of both. The work is mostly carried out in teams of 3-4, using real hardware, and is a mixture of team milestones and individual projects which fit together into a complete system at the end. Emphasis is also placed on a final report which details the complete finished artifact, evaluates its performance, and discusses the choices the team made while building it.
Voraussetzungen / BesonderesThe course is based around a milestone-oriented project, where students work in small groups to implement major components of a microkernel-based operating system. The final assessment will be a combination grades awarded for milestones during the course of the project, a final written report on the work, and a set of test cases run on the final code.
Wahlfächer
NummerTitelTypECTSUmfangDozierende
252-0312-00LUbiquitous Computing Information W4 KP2V + 1AC. Holz, F. Mattern, S. Mayer
KurzbeschreibungUnlike desktop computing, ubiquitous computing occurs anytime and everywhere, using any device, in any location, and in any format. Computers exist in different forms, from watches and phones to refrigerators or pairs of glasses.
Main topics: Smart environments, IoT, mobiles & wearables, context & location, sensing & tracking, computer vision on embedded systems, health monitoring, fabrication.
LernzielUnlike desktop computing, ubiquitous computing occurs anytime and everywhere, using any device, in any location, and in any format. Computers exist in different forms, from watches and phones to refrigerators or pairs of glasses.
Main topics: Smart environments, IoT, mobiles & wearables, context & location, sensing & tracking, computer vision on embedded systems, health monitoring, fabrication.
SkriptCopies of slides will be made available
LiteraturWill be provided in the lecture. To put you in the mood:
Mark Weiser: The Computer for the 21st Century. Scientific American, September 1991, pp. 94-104
252-0437-00LVerteilte Algorithmen Information W5 KP3V + 1AF. Mattern
KurzbeschreibungModelle verteilter Berechnungen; Raum-Zeit Diagramme; Virtuelle Zeit; Logische Uhren und Kausalität; Wellenalgorithmen; Verteilte und parallele Graphtraversierung; Berechnung konsistenter Schnappschüsse; Wechselseitiger Ausschluss; Election und Symmetriebrechung; Verteilte Terminierung; Garbage-Collection in verteilten Systemen; Beobachten verteilter Systeme; Berechnung globaler Prädikate.
LernzielKennenlernen von Modellen und Algorithmen verteilter Systeme.
InhaltVerteilte Algorithmen sind Verfahren, die dadurch charakterisiert sind, dass mehrere autonome Prozesse gleichzeitig Teile eines gemeinsamen Problems in kooperativer Weise bearbeiten und der dabei erforderliche Informationsaustausch ausschliesslich über Nachrichten erfolgt. Derartige Algorithmen kommen im Rahmen verteilter Systeme zum Einsatz, bei denen kein gemeinsamer Speicher existiert und die Übertragungszeit von Nachrichten i.a. nicht vernachlässigt werden kann. Da dabei kein Prozess eine aktuelle konsistente Sicht des globalen Zustands besitzt, führt dies zu interessanten Problemen.
Im einzelnen werden u.a. folgende Themen behandelt:
Modelle verteilter Berechnungen; Raum-Zeit Diagramme; Virtuelle Zeit; Logische Uhren und Kausalität; Wellenalgorithmen; Verteilte und parallele Graphtraversierung; Berechnung konsistenter Schnappschüsse; Wechselseitiger Ausschluss; Election und Symmetriebrechung; Verteilte Terminierung; Garbage-Collection in verteilten Systemen; Beobachten verteilter Systeme; Berechnung globaler Prädikate.
Literatur- F. Mattern: Verteilte Basisalgorithmen, Springer-Verlag
- G. Tel: Topics in Distributed Algorithms, Cambridge University Press
- G. Tel: Introduction to Distributed Algorithms, Cambridge University Press, 2nd edition
- A.D. Kshemkalyani, M. Singhal: Distributed Computing, Cambridge University Press
- N. Lynch: Distributed Algorithms, Morgan Kaufmann Publ
252-0817-00LDistributed Systems Laboratory Information
Im Masterstudium können zusätzlich zu den Vertiefungsübergreifenden Fächern nur max. 10 Kreditpunkte über Laboratorien erarbeitet werden. Weitere Laboratorien werden auf dem Beiblatt aufgeführt.
W10 KP9PG. Alonso, T. Hoefler, F. Mattern, A. Singla, R. Wattenhofer, C. Zhang
KurzbeschreibungEntwicklung und / oder Evaluation eines umfangreicheren praktischen Systems mit Technologien aus dem Gebiet der verteilten Systeme. Das Projekt kann aus unterschiedlichen Teilbereichen (von Web-Services bis hin zu ubiquitären Systemen) stammen; typische Technologien umfassen drahtlose Ad-hoc-Netze oder Anwendungen auf Mobiltelefonen.
LernzielErwerb praktischer Kenntnisse bei Entwicklung und / oder Evaluation eines umfangreicheren praktischen Systems mit Technologien aus dem Gebiet der verteilten Systeme.
InhaltEntwicklung und / oder Evaluation eines umfangreicheren praktischen Systems mit Technologien aus dem Gebiet der verteilten Systeme. Das Projekt kann aus unterschiedlichen Teilbereichen (von Web-Services bis hin zu ubiquitären Systemen) stammen; typische Technologien umfassen drahtlose Ad-hoc-Netze oder Anwendungen auf Mobiltelefonen. Zu diesem Praktikum existiert keine Vorlesung. Bei Interesse bitte einen der beteiligten Professoren oder einen Assistenten der Forschungsgruppen kontaktieren.
263-3710-00LMachine Perception Information Belegung eingeschränkt - Details anzeigen
Number of participants limited to 200.
W5 KP2V + 1U + 1AO. Hilliges
KurzbeschreibungRecent developments in neural networks (aka “deep learning”) have drastically advanced the performance of machine perception systems in a variety of areas including computer vision, robotics, and intelligent UIs. This course is a deep dive into deep learning algorithms and architectures with applications to a variety of perceptual tasks.
LernzielStudents will learn about fundamental aspects of modern deep learning approaches for perception. Students will learn to implement, train and debug their own neural networks and gain a detailed understanding of cutting-edge research in learning-based computer vision, robotics and HCI. The final project assignment will involve training a complex neural network architecture and applying it on a real-world dataset of human activity.

The core competency acquired through this course is a solid foundation in deep-learning algorithms to process and interpret human input into computing systems. In particular, students should be able to develop systems that deal with the problem of recognizing people in images, detecting and describing body parts, inferring their spatial configuration, performing action/gesture recognition from still images or image sequences, also considering multi-modal data, among others.
InhaltWe will focus on teaching: how to set up the problem of machine perception, the learning algorithms, network architectures and advanced deep learning concepts in particular probabilistic deep learning models

The course covers the following main areas:
I) Foundations of deep-learning.
II) Probabilistic deep-learning for generative modelling of data (latent variable models, generative adversarial networks and auto-regressive models).
III) Deep learning in computer vision, human-computer interaction and robotics.

Specific topics include: 
I) Deep learning basics:
a) Neural Networks and training (i.e., backpropagation)
b) Feedforward Networks
c) Timeseries modelling (RNN, GRU, LSTM)
d) Convolutional Neural Networks for classification
II) Probabilistic Deep Learning:
a) Latent variable models (VAEs)
b) Generative adversarial networks (GANs)
c) Autoregressive models (PixelCNN, PixelRNN, TCNs)
III) Deep Learning techniques for machine perception:
a) Fully Convolutional architectures for dense per-pixel tasks (i.e., instance segmentation)
b) Pose estimation and other tasks involving human activity
c) Deep reinforcement learning
IV) Case studies from research in computer vision, HCI, robotics and signal processing
LiteraturDeep Learning
Book by Ian Goodfellow and Yoshua Bengio
Voraussetzungen / BesonderesThis is an advanced grad-level course that requires a background in machine learning. Students are expected to have a solid mathematical foundation, in particular in linear algebra, multivariate calculus, and probability. The course will focus on state-of-the-art research in deep-learning and will not repeat basics of machine learning

Please take note of the following conditions:
1) The number of participants is limited to 200 students (MSc and PhDs).
2) Students must have taken the exam in Machine Learning (252-0535-00) or have acquired equivalent knowledge
3) All practical exercises will require basic knowledge of Python and will use libraries such as TensorFlow, scikit-learn and scikit-image. We will provide introductions to TensorFlow and other libraries that are needed but will not provide introductions to basic programming or Python.

The following courses are strongly recommended as prerequisite:
* "Visual Computing" or "Computer Vision"

The course will be assessed by a final written examination in English. No course materials or electronic devices can be used during the examination. Note that the examination will be based on the contents of the lectures, the associated reading materials and the exercises.
Information Systems
Kernfächer
NummerTitelTypECTSUmfangDozierende
263-2925-00LProgram Analysis for System Security and Reliability Information W6 KP2V + 1U + 2AP. Tsankov
KurzbeschreibungSecurity issues in modern systems (blockchains, datacenters, AI) result in billions of losses due to hacks. This course introduces the security issues in modern systems and state-of-the-art automated techniques for building secure and reliable systems. The course has a practical focus and covers systems built by successful ETH spin-offs.
Lernziel* Learn about security issues in modern systems -- blockchains, smart contracts, AI-based systems (e.g., autonomous cars), data centers -- and why they are challenging to address.

* Understand how the latest automated analysis techniques work, both discrete and probabilistic.

* Understand how these techniques combine with machine-learning methods, both supervised and unsupervised.

* Understand how to use these methods to build reliable and secure modern systems.

* Learn about new open problems that if solved can lead to research and commercial impact.
InhaltPart I: Security of Blockchains

- We will cover existing blockchains (e.g., Ethereum, Bitcoin), how they work, what the core security issues are, and how these have led to massive financial losses.
- We will show how to extract useful information about smart contracts and transactions using interactive analysis frameworks for querying blockchains (e.g. Google's Ethereum BigQuery).
- We will discuss the state-of-the-art security tools (e.g., Link) for ensuring that smart contracts are free of security vulnerabilities.
- We will study the latest automated reasoning systems (e.g., Link) for checking custom (temporal) properties of smart contracts and illustrate their operation on real-world use cases.
- We will study the underlying methods for automated reasoning and testing (e.g., abstract interpretation, symbolic execution, fuzzing) are used to build such tools.


Part II: Security of Datacenters and Networks

- We will show how to ensure that datacenters and ISPs are secured using declarative reasoning methods (e.g., Datalog). We will also see how to automatically synthesize secure configurations (e.g. using SyNET and NetComplete) which lead to desirable behaviors, thus automating the job of the network operator and avoiding critical errors.
- We will discuss how to apply modern discrete probabilistic inference (e.g., PSI and Bayonet) so to reason about probabilistic network properties (e.g., the probability of a packet reaching a destination if links fail).


Part III: Machine Learning for Security

- We will discuss how machine learning models for structured prediction are used to address security tasks, including de-obfuscation of binaries (Debin: Link), Android APKs (DeGuard: Link) and JavaScript (JSNice: Link).
- We will study to leverage program abstractions in combination with clustering techniques to learn security rules for cryptography APIs from large codebases.
- We will study how to automatically learn to identify security vulnerabilities related to the handling of untrusted inputs (cross-Site scripting, SQL injection, path traversal, remote code execution) from large codebases.


To gain a deeper understanding, the course will involve a hands-on programming project where the methods studied in the class will be applied.
Wahlfächer
NummerTitelTypECTSUmfangDozierende
252-0312-00LUbiquitous Computing Information W4 KP2V + 1AC. Holz, F. Mattern, S. Mayer
KurzbeschreibungUnlike desktop computing, ubiquitous computing occurs anytime and everywhere, using any device, in any location, and in any format. Computers exist in different forms, from watches and phones to refrigerators or pairs of glasses.
Main topics: Smart environments, IoT, mobiles & wearables, context & location, sensing & tracking, computer vision on embedded systems, health monitoring, fabrication.
LernzielUnlike desktop computing, ubiquitous computing occurs anytime and everywhere, using any device, in any location, and in any format. Computers exist in different forms, from watches and phones to refrigerators or pairs of glasses.
Main topics: Smart environments, IoT, mobiles & wearables, context & location, sensing & tracking, computer vision on embedded systems, health monitoring, fabrication.
SkriptCopies of slides will be made available
LiteraturWill be provided in the lecture. To put you in the mood:
Mark Weiser: The Computer for the 21st Century. Scientific American, September 1991, pp. 94-104
Software Engineering
Kernfächer
NummerTitelTypECTSUmfangDozierende
263-2925-00LProgram Analysis for System Security and Reliability Information W6 KP2V + 1U + 2AP. Tsankov
KurzbeschreibungSecurity issues in modern systems (blockchains, datacenters, AI) result in billions of losses due to hacks. This course introduces the security issues in modern systems and state-of-the-art automated techniques for building secure and reliable systems. The course has a practical focus and covers systems built by successful ETH spin-offs.
Lernziel* Learn about security issues in modern systems -- blockchains, smart contracts, AI-based systems (e.g., autonomous cars), data centers -- and why they are challenging to address.

* Understand how the latest automated analysis techniques work, both discrete and probabilistic.

* Understand how these techniques combine with machine-learning methods, both supervised and unsupervised.

* Understand how to use these methods to build reliable and secure modern systems.

* Learn about new open problems that if solved can lead to research and commercial impact.
InhaltPart I: Security of Blockchains

- We will cover existing blockchains (e.g., Ethereum, Bitcoin), how they work, what the core security issues are, and how these have led to massive financial losses.
- We will show how to extract useful information about smart contracts and transactions using interactive analysis frameworks for querying blockchains (e.g. Google's Ethereum BigQuery).
- We will discuss the state-of-the-art security tools (e.g., Link) for ensuring that smart contracts are free of security vulnerabilities.
- We will study the latest automated reasoning systems (e.g., Link) for checking custom (temporal) properties of smart contracts and illustrate their operation on real-world use cases.
- We will study the underlying methods for automated reasoning and testing (e.g., abstract interpretation, symbolic execution, fuzzing) are used to build such tools.


Part II: Security of Datacenters and Networks

- We will show how to ensure that datacenters and ISPs are secured using declarative reasoning methods (e.g., Datalog). We will also see how to automatically synthesize secure configurations (e.g. using SyNET and NetComplete) which lead to desirable behaviors, thus automating the job of the network operator and avoiding critical errors.
- We will discuss how to apply modern discrete probabilistic inference (e.g., PSI and Bayonet) so to reason about probabilistic network properties (e.g., the probability of a packet reaching a destination if links fail).


Part III: Machine Learning for Security

- We will discuss how machine learning models for structured prediction are used to address security tasks, including de-obfuscation of binaries (Debin: Link), Android APKs (DeGuard: Link) and JavaScript (JSNice: Link).
- We will study to leverage program abstractions in combination with clustering techniques to learn security rules for cryptography APIs from large codebases.
- We will study how to automatically learn to identify security vulnerabilities related to the handling of untrusted inputs (cross-Site scripting, SQL injection, path traversal, remote code execution) from large codebases.


To gain a deeper understanding, the course will involve a hands-on programming project where the methods studied in the class will be applied.
Wahlfächer
Im FS20 wird keine Veranstaltung in dieser Kategorie angeboten.
Theoretical Computer Science
Kernfächer
NummerTitelTypECTSUmfangDozierende
261-5110-00LOptimization for Data Science Information W8 KP3V + 2U + 2AB. Gärtner, D. Steurer
KurzbeschreibungThis course provides an in-depth theoretical treatment of optimization methods that are particularly relevant in data science.
LernzielUnderstanding the theoretical guarantees (and their limits) of relevant optimization methods used in data science. Learning general paradigms to deal with optimization problems arising in data science.
InhaltThis course provides an in-depth theoretical treatment of optimization methods that are particularly relevant in machine learning and data science.

In the first part of the course, we will first give a brief introduction to convex optimization, with some basic motivating examples from machine learning. Then we will analyse classical and more recent first and second order methods for convex optimization: gradient descent, projected gradient descent, subgradient descent, stochastic gradient descent, Nesterov's accelerated method, Newton's method, and Quasi-Newton methods. The emphasis will be on analysis techniques that occur repeatedly in convergence analyses for various classes of convex functions. We will also discuss some classical and recent theoretical results for nonconvex optimization.

In the second part, we discuss convex programming relaxations as a powerful and versatile paradigm for designing efficient algorithms to solve computational problems arising in data science. We will learn about this paradigm and develop a unified perspective on it through the lens of the sum-of-squares semidefinite programming hierarchy. As applications, we are discussing non-negative matrix factorization, compressed sensing and sparse linear regression, matrix completion and phase retrieval, as well as robust estimation.
Voraussetzungen / BesonderesAs background, we require material taught in the course "252-0209-00L Algorithms, Probability, and Computing". It is not necessary that participants have actually taken the course, but they should be prepared to catch up if necessary.
Wahlfächer
NummerTitelTypECTSUmfangDozierende
252-1424-00LModels of ComputationW6 KP2V + 2U + 1AM. Cook
KurzbeschreibungThis course surveys many different models of computation: Turing Machines, Cellular Automata, Finite State Machines, Graph Automata, Circuits, Tilings, Lambda Calculus, Fractran, Chemical Reaction Networks, Hopfield Networks, String Rewriting Systems, Tag Systems, Diophantine Equations, Register Machines, Primitive Recursive Functions, and more.
LernzielThe goal of this course is to become acquainted with a wide variety of models of computation, to understand how models help us to understand the modeled systems, and to be able to develop and analyze models appropriate for new systems.
InhaltThis course surveys many different models of computation: Turing Machines, Cellular Automata, Finite State Machines, Graph Automata, Circuits, Tilings, Lambda Calculus, Fractran, Chemical Reaction Networks, Hopfield Networks, String Rewriting Systems, Tag Systems, Diophantine Equations, Register Machines, Primitive Recursive Functions, and more.
272-0302-00LApproximations- und Online-Algorithmen Information W5 KP2V + 1U + 1AH.‑J. Böckenhauer, D. Komm
KurzbeschreibungDiese Lerneinheit behandelt approximative Verfahren für schwere Optimierungsprobleme und algorithmische Ansätze zur Lösung von Online-Problemen sowie die Grenzen dieser Ansätze.
LernzielAuf systematische Weise einen Überblick über die verschiedenen Entwurfsmethoden von approximativen Verfahren für schwere Optimierungsprobleme und Online-Probleme zu gewinnen. Methoden kennenlernen, die Grenzen dieser Ansätze aufweisen.
InhaltApproximationsalgorithmen sind einer der erfolgreichsten Ansätze zur Behandlung schwerer Optimierungsprobleme. Dabei untersucht man die sogenannte Approximationsgüte, also das Verhältnis der Kosten einer berechneten Näherungslösung und der Kosten einer (nicht effizient berechenbaren) optimalen Lösung.
Bei einem Online-Problem ist nicht die gesamte Eingabe von Anfang an bekannt, sondern sie erscheint stückweise und für jeden Teil der Eingabe muss sofort ein entsprechender Teil der endgültigen Ausgabe produziert werden. Die Güte eines Algorithmus für ein Online-Problem misst man mit der competitive ratio, also dem Verhältnis der Kosten der berechneten Lösung und der Kosten einer optimalen Lösung, wie man sie berechnen könnte, wenn die gesamte Eingabe bekannt wäre.

Inhalt dieser Lerneinheit sind
- die Klassifizierung von Optimierungsproblemen nach der erreichbaren Approximationsgüte,
- systematische Methoden zum Entwurf von Approximationsalgorithmen (z. B. Greedy-Strategien, dynamische Programmierung, LP-Relaxierung),
- Methoden zum Nachweis der Nichtapproximierbarkeit,
- klassische Online-Probleme wie Paging oder Scheduling-Probleme und Algorithmen zu ihrer Lösung,
- randomisierte Online-Algorithmen,
- Entwurfs- und Analyseverfahren für Online-Algorithmen,
- Grenzen des "competitive ratio"- Modells und Advice-Komplexität als eine Möglichkeit, die Komplexität von Online-Problemen genauer zu messen.
LiteraturDie Vorlesung orientiert sich teilweise an folgenden Büchern:

J. Hromkovic: Algorithmics for Hard Problems, Springer, 2004

D. Komm: An Introduction to Online Computation: Determinism, Randomization, Advice, Springer, 2016

Zusätzliche Literatur:

A. Borodin, R. El-Yaniv: Online Computation and Competitive Analysis, Cambridge University Press, 1998
263-4400-00LAdvanced Graph Algorithms and Optimization Information Belegung eingeschränkt - Details anzeigen
Number of participants limited to 30.
W5 KP3G + 1AR. Kyng
KurzbeschreibungThis course will cover a number of advanced topics in optimization and graph algorithms.
LernzielThe course will take students on a deep dive into modern approaches to
graph algorithms using convex optimization techniques.

By studying convex optimization through the lens of graph algorithms,
students should develop a deeper understanding of fundamental
phenomena in optimization.

The course will cover some traditional discrete approaches to various graph
problems, especially flow problems, and then contrast these approaches
with modern, asymptotically faster methods based on combining convex
optimization with spectral and combinatorial graph theory.
InhaltStudents should leave the course understanding key
concepts in optimization such as first and second-order optimization,
convex duality, multiplicative weights and dual-based methods,
acceleration, preconditioning, and non-Euclidean optimization.

Students will also be familiarized with central techniques in the
development of graph algorithms in the past 15 years, including graph
decomposition techniques, sparsification, oblivious routing, and
spectral and combinatorial preconditioning.
Voraussetzungen / BesonderesThis course is targeted toward masters and doctoral students with an
interest in theoretical computer science.

Students should be comfortable with design and analysis of algorithms, probability, and linear algebra.

Having passed the course Algorithms, Probability, and Computing (APC) is highly recommended, but not formally required. If you are not
sure whether you're ready for this class or not, please consult the
instructor.
401-3052-05LGraph Theory Information W5 KP2V + 1UB. Sudakov
KurzbeschreibungBasic notions, trees, spanning trees, Caley's formula, vertex and edge connectivity, 2-connectivity, Mader's theorem, Menger's theorem, Eulerian graphs, Hamilton cycles, Dirac's theorem, matchings, theorems of Hall, König and Tutte, planar graphs, Euler's formula, basic non-planar graphs, graph colorings, greedy colorings, Brooks' theorem, 5-colorings of planar graphs
LernzielThe students will get an overview over the most fundamental questions concerning graph theory. We expect them to understand the proof techniques and to use them autonomously on related problems.
SkriptLecture will be only at the blackboard.
LiteraturWest, D.: "Introduction to Graph Theory"
Diestel, R.: "Graph Theory"

Further literature links will be provided in the lecture.
Voraussetzungen / BesonderesStudents are expected to have a mathematical background and should be able to write rigorous proofs.


NOTICE: This course unit was previously offered as 252-1408-00L Graphs and Algorithms.
401-3903-11LGeometric Integer ProgrammingW6 KP2V + 1UJ. Paat
KurzbeschreibungInteger programming is the task of minimizing a linear function over all the integer points in a polyhedron. This lecture introduces the key concepts of an algorithmic theory for solving such problems.
LernzielThe purpose of the lecture is to provide a geometric treatment of the theory of integer optimization.
InhaltKey topics are:

- Lattice theory and the polynomial time solvability of integer optimization problems in fixed dimension.

- Structural properties of integer sets that reveal other parameters affecting the complexity of integer problems

- Duality theory for integer optimization problems from the vantage point of lattice free sets.
Skriptnot available, blackboard presentation
LiteraturLecture notes will be provided.

Other helpful materials include

Bertsimas, Weismantel: Optimization over Integers, 2005

and

Schrijver: Theory of linear and integer programming, 1986.
Voraussetzungen / Besonderes"Mathematical Optimization" (401-3901-00L)
Visual Computing
Kernfächer
NummerTitelTypECTSUmfangDozierende
252-0538-00LShape Modeling and Geometry Processing Information W6 KP2V + 1U + 2AO. Sorkine Hornung
KurzbeschreibungThis course covers the fundamentals and some of the latest developments in geometric modeling and geometry processing. Topics include surface modeling based on point clouds and polygonal meshes, mesh generation, surface reconstruction, mesh fairing and parameterization, discrete differential geometry, interactive shape editing, topics in digital shape fabrication.
LernzielThe students will learn how to design, program and analyze algorithms and systems for interactive 3D shape modeling and geometry processing.
InhaltRecent advances in 3D geometry processing have created a plenitude of novel concepts for the mathematical representation and interactive manipulation of geometric models. This course covers the fundamentals and some of the latest developments in geometric modeling and geometry processing. Topics include surface modeling based on point clouds and triangle meshes, mesh generation, surface reconstruction, mesh fairing and parameterization, discrete differential geometry, interactive shape editing and digital shape fabrication.
SkriptSlides and course notes
Voraussetzungen / BesonderesPrerequisites:
Visual Computing, Computer Graphics or an equivalent class. Experience with C++ programming. Solid background in linear algebra and analysis. Some knowledge of differential geometry, computational geometry and numerical methods is helpful but not a strict requirement.
Wahlfächer
NummerTitelTypECTSUmfangDozierende
252-0526-00LStatistical Learning Theory Information W7 KP3V + 2U + 1AJ. M. Buhmann, C. Cotrini Jimenez
KurzbeschreibungThe course covers advanced methods of statistical learning:

- Variational methods and optimization.
- Deterministic annealing.
- Clustering for diverse types of data.
- Model validation by information theory.
LernzielThe course surveys recent methods of statistical learning. The fundamentals of machine learning, as presented in the courses "Introduction to Machine Learning" and "Advanced Machine Learning", are expanded from the perspective of statistical learning.
Inhalt- Variational methods and optimization. We consider optimization approaches for problems where the optimizer is a probability distribution. We will discuss concepts like maximum entropy, information bottleneck, and deterministic annealing.

- Clustering. This is the problem of sorting data into groups without using training samples. We discuss alternative notions of "similarity" between data points and adequate optimization procedures.

- Model selection and validation. This refers to the question of how complex the chosen model should be. In particular, we present an information theoretic approach for model validation.

- Statistical physics models. We discuss approaches for approximately optimizing large systems, which originate in statistical physics (free energy minimization applied to spin glasses and other models). We also study sampling methods based on these models.
SkriptA draft of a script will be provided. Lecture slides will be made available.
LiteraturHastie, Tibshirani, Friedman: The Elements of Statistical Learning, Springer, 2001.

L. Devroye, L. Gyorfi, and G. Lugosi: A probabilistic theory of pattern recognition. Springer, New York, 1996
Voraussetzungen / BesonderesKnowledge of machine learning (introduction to machine learning and/or advanced machine learning)
Basic knowledge of statistics.
252-0570-00LGame Programming Laboratory Information
Im Masterstudium können zusätzlich zu den Vertiefungsübergreifenden Fächern nur max. 10 Kreditpunkte über Laboratorien erarbeitet werden. Weitere Laboratorien werden auf dem Beiblatt aufgeführt.
W10 KP9PB. Sumner
KurzbeschreibungDas Ziel dieses Kurses ist ein vertieftes Verständnis der Technologie und der Programmierung von Computer-Spielen. Die Studierenden entwerfen und entwickeln in kleinen Gruppen ein Computer-Spiel und machen sich so vertraut mit der Kunst des Spiel-Programmierens.
LernzielDas Ziel dieses neuen Kurses ist es, die Studenten mit der Technologie und der Kunst des Programmierens von modernen dreidimensionalen Computerspielen vertraut zu machen.
InhaltDies ist ein Kurs, der auf die Technologie von modernen dreidimensionalen Computerspielen eingeht. Während des Kurses werden die Studenten in kleinen Gruppen ein Computerspiel entwerfen und entwickeln. Der Schwerpunkt des Kurses wird auf technischen Aspekten der Spielentwicklung wie Rendering, Kinematographie, Interaktion, Physik, Animation und KI liegen. Zusätzlich werden wir aber auch Wert auf kreative Ideen für fortgeschrittenes Gameplay und visuelle Effekte legen.

Der Kurs wird als Labor durchgeführt. Zusätzlich zu Vorträgen und Übungen wird der Kurs in einen praktischen, hands-on Ansatz durchgeführt. Wir treffen uns einmal wöchentlich um technische Aspekte zu besprechen und den Fortschritt der Entwicklung zu verfolgen. Für die Enwicklung verwenden wir MonoGames. Dies ist eine Ansammlung von Bibliotheken und Werkzeugen um die Spieleentwicklung zu erleichtern. Die Entwicklung wird zunächst auf dem PC stattfinden, das Spiel wird dann im weiteren Verlauf auf der Xbox One Konsole eingesetzt.

Am Ende des Kurses werden die Resultate öffentlich präsentiert.
SkriptGame Design Workshop: A Playcentric Approach to Creating Innovative Games by Tracy Fullerton
Voraussetzungen / BesonderesDie Anzahl der Teilnehmer ist begrenzt.

Voraussetzung für die Teilnahme sind:

- Gute Programmierkenntnisse (Java, C++, C#, o.ä.)

- Erfahrung in Computergrafik: Teilnehmer sollten mindestens die Vorlesung Visual Computing besucht haben. Wir empfehlen auch noch die weiterführenden Kurse Introduction to Computer Graphics, Surface Representations and Geometric Modeling, und Physically-based Simulation in Computer Graphics.
252-0579-00L3D Vision Information W5 KP3G + 1AM. Pollefeys, V. Larsson
KurzbeschreibungThe course covers camera models and calibration, feature tracking and matching, camera motion estimation via simultaneous localization and mapping (SLAM) and visual odometry (VO), epipolar and mult-view geometry, structure-from-motion, (multi-view) stereo, augmented reality, and image-based (re-)localization.
LernzielAfter attending this course, students will:
1. understand the core concepts for recovering 3D shape of objects and scenes from images and video.
2. be able to implement basic systems for vision-based robotics and simple virtual/augmented reality applications.
3. have a good overview over the current state-of-the art in 3D vision.
4. be able to critically analyze and asses current research in this area.
InhaltThe goal of this course is to teach the core techniques required for robotic and augmented reality applications: How to determine the motion of a camera and how to estimate the absolute position and orientation of a camera in the real world. This course will introduce the basic concepts of 3D Vision in the form of short lectures, followed by student presentations discussing the current state-of-the-art. The main focus of this course are student projects on 3D Vision topics, with an emphasis on robotic vision and virtual and augmented reality applications.
252-5706-00LMathematical Foundations of Computer Graphics and Vision Information W5 KP2V + 1U + 1AM. R. Oswald, C. Öztireli
KurzbeschreibungThis course presents the fundamental mathematical tools and concepts used in computer graphics and vision. Each theoretical topic is introduced in the context of practical vision or graphic problems, showcasing its importance in real-world applications.
LernzielThe main goal is to equip the students with the key mathematical tools necessary to understand state-of-the-art algorithms in vision and graphics. In addition to the theoretical part, the students will learn how to use these mathematical tools to solve a wide range of practical problems in visual computing. After successfully completing this course, the students will be able to apply these mathematical concepts and tools to practical industrial and academic projects in visual computing.
InhaltThe theory behind various mathematical concepts and tools will be introduced, and their practical utility will be showcased in diverse applications in computer graphics and vision. The course will cover topics in sampling, reconstruction, approximation, optimization, robust fitting, differentiation, quadrature and spectral methods. Applications will include 3D surface reconstruction, camera pose estimation, image editing, data projection, character animation, structure-aware geometry processing, and rendering.
263-3710-00LMachine Perception Information Belegung eingeschränkt - Details anzeigen
Number of participants limited to 200.
W5 KP2V + 1U + 1AO. Hilliges
KurzbeschreibungRecent developments in neural networks (aka “deep learning”) have drastically advanced the performance of machine perception systems in a variety of areas including computer vision, robotics, and intelligent UIs. This course is a deep dive into deep learning algorithms and architectures with applications to a variety of perceptual tasks.
LernzielStudents will learn about fundamental aspects of modern deep learning approaches for perception. Students will learn to implement, train and debug their own neural networks and gain a detailed understanding of cutting-edge research in learning-based computer vision, robotics and HCI. The final project assignment will involve training a complex neural network architecture and applying it on a real-world dataset of human activity.

The core competency acquired through this course is a solid foundation in deep-learning algorithms to process and interpret human input into computing systems. In particular, students should be able to develop systems that deal with the problem of recognizing people in images, detecting and describing body parts, inferring their spatial configuration, performing action/gesture recognition from still images or image sequences, also considering multi-modal data, among others.
InhaltWe will focus on teaching: how to set up the problem of machine perception, the learning algorithms, network architectures and advanced deep learning concepts in particular probabilistic deep learning models

The course covers the following main areas:
I) Foundations of deep-learning.
II) Probabilistic deep-learning for generative modelling of data (latent variable models, generative adversarial networks and auto-regressive models).
III) Deep learning in computer vision, human-computer interaction and robotics.

Specific topics include: 
I) Deep learning basics:
a) Neural Networks and training (i.e., backpropagation)
b) Feedforward Networks
c) Timeseries modelling (RNN, GRU, LSTM)
d) Convolutional Neural Networks for classification
II) Probabilistic Deep Learning:
a) Latent variable models (VAEs)
b) Generative adversarial networks (GANs)
c) Autoregressive models (PixelCNN, PixelRNN, TCNs)
III) Deep Learning techniques for machine perception:
a) Fully Convolutional architectures for dense per-pixel tasks (i.e., instance segmentation)
b) Pose estimation and other tasks involving human activity
c) Deep reinforcement learning
IV) Case studies from research in computer vision, HCI, robotics and signal processing
LiteraturDeep Learning
Book by Ian Goodfellow and Yoshua Bengio
Voraussetzungen / BesonderesThis is an advanced grad-level course that requires a background in machine learning. Students are expected to have a solid mathematical foundation, in particular in linear algebra, multivariate calculus, and probability. The course will focus on state-of-the-art research in deep-learning and will not repeat basics of machine learning

Please take note of the following conditions:
1) The number of participants is limited to 200 students (MSc and PhDs).
2) Students must have taken the exam in Machine Learning (252-0535-00) or have acquired equivalent knowledge
3) All practical exercises will require basic knowledge of Python and will use libraries such as TensorFlow, scikit-learn and scikit-image. We will provide introductions to TensorFlow and other libraries that are needed but will not provide introductions to basic programming or Python.

The following courses are strongly recommended as prerequisite:
* "Visual Computing" or "Computer Vision"

The course will be assessed by a final written examination in English. No course materials or electronic devices can be used during the examination. Note that the examination will be based on the contents of the lectures, the associated reading materials and the exercises.
263-5806-00LComputational Models of Motion for Character Animation and Robotics Information W6 KP2V + 2U + 1AS. Coros, M. Bächer, B. Thomaszewski
KurzbeschreibungThis course covers fundamentals of physics-based modelling and numerical optimization from the perspective of character animation and robotics applications. The methods discussed in class derive their theoretical underpinnings from applied mathematics, control theory and computational mechanics, and they will be richly illustrated using examples ranging from locomotion controllers and crowd simula
LernzielStudents will learn how to represent, model and algorithmically control the behavior of animated characters and real-life robots. The lectures are accompanied by programming assignments (written in C++) and a capstone project.
InhaltOptimal control and trajectory optimization; multibody systems; kinematics; forward and inverse dynamics; constrained and unconstrained numerical optimization; mass-spring models for crowd simulation; FEM; compliant systems; sim-to-real; robotic manipulation of elastically-deforming objects.
Voraussetzungen / BesonderesExperience with C++ programming, numerical linear algebra and multivariate calculus. Some background in physics-based modeling, kinematics and dynamics is helpful, but not necessary.
227-1034-00LComputational Vision (University of Zurich)
No enrolment to this course at ETH Zurich. Book the corresponding module directly at UZH.
UZH Module Code: INI402

Mind the enrolment deadlines at UZH:
Link
W6 KP2V + 1UD. Kiper
KurzbeschreibungThis course focuses on neural computations that underlie visual perception. We study how visual signals are processed in the retina, LGN and visual cortex. We study the morpholgy and functional architecture of cortical circuits responsible for pattern, motion, color, and three-dimensional vision.
LernzielThis course considers the operation of circuits in the process of neural computations. The evolution of neural systems will be considered to demonstrate how neural structures and mechanisms are optimised for energy capture, transduction, transmission and representation of information. Canonical brain circuits will be described as models for the analysis of sensory information. The concept of receptive fields will be introduced and their role in coding spatial and temporal information will be considered. The constraints of the bandwidth of neural channels and the mechanisms of normalization by neural circuits will be discussed.
The visual system will form the basis of case studies in the computation of form, depth, and motion. The role of multiple channels and collective computations for object recognition will
be considered. Coordinate transformations of space and time by cortical and subcortical mechanisms will be analysed. The means by which sensory and motor systems are integrated to allow for adaptive behaviour will be considered.
InhaltThis course considers the operation of circuits in the process of neural computations. The evolution of neural systems will be considered to demonstrate how neural structures and mechanisms are optimised for energy capture, transduction, transmission and representation of information. Canonical brain circuits will be described as models for the analysis of sensory information. The concept of receptive fields will be introduced and their role in coding spatial and temporal information will be considered. The constraints of the bandwidth of neural channels and the mechanisms of normalization by neural circuits will be discussed.
The visual system will form the basis of case studies in the computation of form, depth, and motion. The role of multiple channels and collective computations for object recognition will
be considered. Coordinate transformations of space and time by cortical and subcortical mechanisms will be analysed. The means by which sensory and motor systems are integrated to allow for adaptive behaviour will be considered.
LiteraturBooks: (recommended references, not required)
1. An Introduction to Natural Computation, D. Ballard (Bradford Books, MIT Press) 1997.
2. The Handbook of Brain Theorie and Neural Networks, M. Arbib (editor), (MIT Press) 1995.
Vertiefungsübergreifende Fächer
NummerTitelTypECTSUmfangDozierende
263-0007-00LAdvanced Systems Lab Information Belegung eingeschränkt - Details anzeigen
Only for master students, otherwise a special permission by the study administration of D-INFK is required.
W8 KP3V + 2U + 2AM. Püschel, C. Zhang
KurzbeschreibungThis course introduces the student to the foundations and state-of-the-art techniques in developing high performance software for mathematical functionality occurring in various fields in computer science. The focus is on optimizing for a single core and includes optimizing for the memory hierarchy, for special instruction sets, and the possible use of automatic performance tuning.
LernzielSoftware performance (i.e., runtime) arises through the complex interaction of algorithm, its implementation, the compiler used, and the microarchitecture the program is run on. The first goal of the course is to provide the student with an understanding of this "vertical" interaction, and hence software performance, for mathematical functionality. The second goal is to teach a systematic strategy how to use this knowledge to write fast software for numerical problems. This strategy will be trained in several homeworks and a semester-long group project.
InhaltThe fast evolution and increasing complexity of computing platforms pose a major challenge for developers of high performance software for engineering, science, and consumer applications: it becomes increasingly harder to harness the available computing power. Straightforward implementations may lose as much as one or two orders of magnitude in performance. On the other hand, creating optimal implementations requires the developer to have an understanding of algorithms, capabilities and limitations of compilers, and the target platform's architecture and microarchitecture.

This interdisciplinary course introduces the student to the foundations and state-of-the-art techniques in high performance mathematical software development using important functionality such as matrix operations, transforms, filters, and others as examples. The course will explain how to optimize for the memory hierarchy, take advantage of special instruction sets, and other details of current processors that require optimization. The concept of automatic performance tuning is introduced. The focus is on optimization for a single core; thus, the course complements others on parallel and distributed computing.

Finally a general strategy for performance analysis and optimization is introduced that the students will apply in group projects that accompany the course.
Voraussetzungen / BesonderesSolid knowledge of the C programming language and matrix algebra.
263-0008-00LComputational Intelligence Lab
Only for master students, otherwise a special permission by the study administration of D-INFK is required.
W8 KP2V + 2U + 3AT. Hofmann
KurzbeschreibungThis laboratory course teaches fundamental concepts in computational science and machine learning with a special emphasis on matrix factorization and representation learning. The class covers techniques like dimension reduction, data clustering, sparse coding, and deep learning as well as a wide spectrum of related use cases and applications.
LernzielStudents acquire fundamental theoretical concepts and methodologies from machine learning and how to apply these techniques to build intelligent systems that solve real-world problems. They learn to successfully develop solutions to application problems by following the key steps of modeling, algorithm design, implementation and experimental validation.

This lab course has a strong focus on practical assignments. Students work in groups of three to four people, to develop solutions to three application problems: 1. Collaborative filtering and recommender systems, 2. Text sentiment classification, and 3. Road segmentation in aerial imagery.

For each of these problems, students submit their solutions to an online evaluation and ranking system, and get feedback in terms of numerical accuracy and computational speed. In the final part of the course, students combine and extend one of their previous promising solutions, and write up their findings in an extended abstract in the style of a conference paper.

(Disclaimer: The offered projects may be subject to change from year to year.)
Inhaltsee course description
Freie Wahlfächer
Den Studierenden stehen alle MSc Lehrveranstaltungent der ETHZ, der EPFL Lausanne und der Universität Zürich zur individuellen Auswahl offen.
» Auswahl aus sämtlichen Lehrveranstaltungen der ETH Zürich
GESS Wissenschaft im Kontext
» Empfehlungen aus dem Bereich GESS Wissenschaft im Kontext (Typ B) für das D-INFK.
» siehe Studiengang GESS Wissenschaft im Kontext: Typ A: Förderung allgemeiner Reflexionsfähigkeiten
» siehe Studiengang GESS Wissenschaft im Kontext: Sprachkurse ETH/UZH
Industriepraktikum
NummerTitelTypECTSUmfangDozierende
260-0700-00LPraktikum
Only for Cyber Security MSc
E-0 KPexterne Veranstalter
KurzbeschreibungZiel eines Praktikums ist es, den Studierenden industrielle Arbeitsumgebungen näher zu bringen. Dabei bietet sich ihnen die Gelegenheit, in aktuelle Projekte der betreffenden Institution involviert zu werden.
Lernzielsiehe oben
Master-Arbeit
NummerTitelTypECTSUmfangDozierende
260-0800-00LMaster's Thesis Belegung eingeschränkt - Details anzeigen
Zur Master-Arbeit wird nur zugelassen, wer:
a. das Bachelor-Studium erfolgreich abgeschlossen hat;
b. allfällige Auflagen für die Zulassung zum Master-Studiengang erfüllt hat.
O30 KP64DProfessor/innen
KurzbeschreibungDie Master-Arbeit bildet den Abschluss des Master-Studiums. Die Studierenden sollen mit der Master-Arbeit ihre Fähigkeit zu selbständiger und wissenschaftlich strukturierter Arbeit nachweisen.
LernzielMit der Master-Arbeit sollen die Studierenden Ihre Fähigkeit zu selbständiger und wissenschaftlich strukturierter Tätigkeit aufzeigen.