227-1048-00L  Neuromorphic Intelligence (University of Zurich)

SemesterSpring Semester 2021
LecturersG. Indiveri, E. Donati
Periodicityyearly recurring course
Language of instructionEnglish
CommentNo enrolment to this course at ETH Zurich. Book the corresponding module directly at UZH.
UZH Module Code: INI508

Mind the enrolment deadlines at UZH:
Link



Courses

NumberTitleHoursLecturers
227-1048-00 VNeuromorphic Intelligence (University of Zurich)
**Course at University of Zurich**

Location: please see VVZ UZH
2 hrs
Tue16:15-18:00UNI ZH .
G. Indiveri, E. Donati

Catalogue data

AbstractIn this course we will study the computational properties of spiking neural networks implemented using analog "neuromorphic" electronic circuits. We will present network architectures and computational primitives that can use the dynamics of these circuits to exhibit intelligent behaviors. We will characterize these networks and validate them using full custom chips in laboratory experiments.
ObjectiveThe objective of this course is to introduce students to the field of “neuromorphic intelligence” with lectures on spiking neural network architectures implemented using mixed-signal silicon neuron and synapse circuits, and with laboratory sessions using neuromorphic chips to measure the computational properties of different spiking neural network architectures. Class projects will be proposed to validate the models presented in the lectures and carry out real-time signal processing and pattern recognition tasks on real-world sensory data.
ContentStudents will learn about the dynamical properties of adaptive integrate and fire neurons connected with each other via dynamic synapses. They will explore different neural circuits configured to implement computational primitives such as normalization, winner-take-all computation, selective amplification, and pattern discrimination. The experiments will consist of measuring the properties of real silicon neurons using full-custom neuromorphic processors, and configuring them to create neural architectures that can robustly process sensory signals and perform pattern discrimination despite, or thanks to, the limited resolution and large variability of their individual processing
element
Prerequisites / NoticeAccessible to NSC Master students.
It is recommended (but not mandatory) to have taken the Introduction to Neuroinformatics course (INI-401/227-1037-00).

Performance assessment

Performance assessment information (valid until the course unit is held again)
Performance assessment as a semester course
ECTS credits6 credits
ExaminersG. Indiveri, E. Donati
Typegraded semester performance
Language of examinationEnglish
RepetitionRepetition only possible after re-enrolling for the course unit.
Additional information on mode of examinationRegistration modalities, date and venue of this performance assessment are specified solely by the UZH.

Learning materials

No public learning materials available.
Only public learning materials are listed.

Groups

No information on groups available.

Restrictions

There are no additional restrictions for the registration.

Offered in

ProgrammeSectionType
Neural Systems and Computation MasterElectivesWInformation
Neural Systems and Computation MasterNeurotechnologies and Neuromorphic EngineeringWInformation