252-0220-00L  Introduction to Machine Learning

SemesterSpring Semester 2022
LecturersA. Krause, F. Yang
Periodicityyearly recurring course
Language of instructionEnglish
CommentLimited number of participants. Preference is given to students in programmes in which the course is being offered. All other students will be waitlisted. Please do not contact Prof. Krause for any questions in this regard. If necessary, please contact studiensekretariat@inf.ethz.ch



Courses

NumberTitleHoursLecturers
252-0220-00 VIntroduction to Machine Learning
Findet im ETA F 5 mit Videoübertragung ins ETF E 1 statt
4 hrs
Tue14:15-16:00ETA F 5 »
14:15-16:00ETF E 1 »
Wed14:15-16:00ETA F 5 »
14:15-16:00ETF E 1 »
A. Krause, F. Yang
252-0220-00 UIntroduction to Machine Learning2 hrs
Fri14:15-16:00ML D 28 »
A. Krause, F. Yang
252-0220-00 AIntroduction to Machine Learning
No presence required.
1 hrsA. Krause, F. Yang

Catalogue data

AbstractThe course introduces the foundations of learning and making predictions based on data.
Learning objectiveThe course will introduce the foundations of learning and making predictions from data. We will study basic concepts such as trading goodness of fit and model complexitiy. We will discuss important machine learning algorithms used in practice, and provide hands-on experience in a course project.
Content- Linear regression (overfitting, cross-validation/bootstrap, model selection, regularization, [stochastic] gradient descent)
- Linear classification: Logistic regression (feature selection, sparsity, multi-class)
- Kernels and the kernel trick (Properties of kernels; applications to linear and logistic regression); k-nearest neighbor
- Neural networks (backpropagation, regularization, convolutional neural networks)
- Unsupervised learning (k-means, PCA, neural network autoencoders)
- The statistical perspective (regularization as prior; loss as likelihood; learning as MAP inference)
- Statistical decision theory (decision making based on statistical models and utility functions)
- Discriminative vs. generative modeling (benefits and challenges in modeling joint vy. conditional distributions)
- Bayes' classifiers (Naive Bayes, Gaussian Bayes; MLE)
- Bayesian approaches to unsupervised learning (Gaussian mixtures, EM)
LiteratureTextbook: Kevin Murphy, Machine Learning: A Probabilistic Perspective, MIT Press
Prerequisites / NoticeDesigned to provide a basis for following courses:
- Advanced Machine Learning
- Deep Learning
- Probabilistic Artificial Intelligence
- Seminar "Advanced Topics in Machine Learning"

Performance assessment

Performance assessment information (valid until the course unit is held again)
Performance assessment as a semester course
ECTS credits8 credits
ExaminersA. Krause, F. Yang
Typesession examination
Language of examinationEnglish
RepetitionThe performance assessment is offered every session. Repetition possible without re-enrolling for the course unit.
Mode of examinationwritten 120 minutes
Additional information on mode of examination70% session examination, 30% project; the final grade will be calculated as weighted average of both these elements. As a compulsory continuous performance assessment task, the project must be passed on its own and has a bonus/penalty function.

The practical projects are an integral part (60 hours of work, 2 credits) of the course. Participation is mandatory.
Failing the project results in a failing grade for the overall examination of Introduction to Machine Learning (252-0220-00L).
Students who do not pass the project are required to de-register from the exam and will otherwise be treated as a no show.

Exceptionally, an examination during the winter examination session 2023 will be offered.
Written aidsTwo A4-pages (i.e. one A4-sheet of paper), either handwritten or 11 point minimum font size.
Simple non-programmable calculator
Digital examThe exam takes place on devices provided by ETH Zurich.
This information can be updated until the beginning of the semester; information on the examination timetable is binding.

Learning materials

 
Main linkInformation
Only public learning materials are listed.

Groups

No information on groups available.

Restrictions

Places800 at the most
PriorityRegistration for the course unit is until 06.03.2022 only possible for the primary target group
Primary target groupIntegrated Building Systems MSc (062000)
Mechanical Engineering BSc (152000)
Robotics, Systems and Control MSc (159000)
Mechanical Engineering MSc (162000)
Electrical Engin. + Information Technology BSc (228000)
Quantum Engineering MSc (235000)
Electrical Engin. + Information Technology MSc (237000)
Biomedical Engineering MSc (238000)
Computer Science BSc (252000)
Computational Biology and Bioinformatics MSc (262200)
Computer Science MSc (263000)
Doctorate Computer Science (264002)
DAS ETH in Data Science (266000)
Computer Science (Mobility) (274000)
Management, Technology, and Economics MSc (363000)
Mathematics BSc (404000)
Computational Science and Engineering BSc (406000)
Quantitative Finance MSc (435000)
Statistics MSc (436000)
Computational Science and Engineering MSc (438000)
MAS Medical Physics (Radiation Therapy) (465100)
MAS Medical Physics (General Medical Physics) (465200)
Science, Technology and Policy MSc (860000)
Waiting listuntil 13.03.2022
End of registration periodRegistration only possible until 13.03.2022

Offered in

ProgrammeSectionType
Biomedical Engineering MasterRecommended Elective CoursesWInformation
Biomedical Engineering MasterRecommended Elective CoursesWInformation
Computational Biology and Bioinformatics MasterData ScienceWInformation
DAS in Data ScienceFoundations CoursesWInformation
Electrical Engineering and Information Technology BachelorEngineering ElectivesWInformation
Electrical Engineering and Information Technology MasterFoundation Core CoursesWInformation
Electrical Engineering and Information Technology MasterCore SubjectsWInformation
Computer Science BachelorMajor: Information and Data ProcessingOInformation
Integrated Building Systems MasterSpecialised CoursesWInformation
MAS in Medical PhysicsCore CoursesWInformation
Mechanical Engineering BachelorMechatronics and RoboticsWInformation
Mechanical Engineering MasterMechanics, Materials, StructuresWInformation
Mechanical Engineering MasterRobotics, Systems and ControlWInformation
Mathematics BachelorSelection: Further RealmsWInformation
Physics MasterGeneral ElectivesWInformation
Quantitative Finance MasterMathematical Methods for FinanceWInformation
Quantum Engineering MasterElectivesWInformation
Computational Science and Engineering BachelorCore Courses from Group IIWInformation
Computational Science and Engineering BachelorRoboticsWInformation
Computational Science and Engineering MasterRoboticsWInformation
Robotics, Systems and Control MasterCore CoursesWInformation
Science, Technology, and Policy MasterData and Computer ScienceWInformation
Statistics MasterStatistical and Mathematical CoursesWInformation
Statistics MasterSubject Specific ElectivesWInformation