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

SemesterFrühjahrssemester 2021
DozierendeG. Indiveri, E. Donati
Periodizitätjährlich wiederkehrende Veranstaltung
LehrspracheEnglisch
KommentarNo 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



Lehrveranstaltungen

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

Location: please see VVZ UZH
2 Std.
Di16:15-18:00UNI ZH .
G. Indiveri, E. Donati

Katalogdaten

KurzbeschreibungIn 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.
LernzielThe 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.
InhaltStudents 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
Voraussetzungen / BesonderesAccessible to NSC Master students.
It is recommended (but not mandatory) to have taken the Introduction to Neuroinformatics course (INI-401/227-1037-00).

Leistungskontrolle

Information zur Leistungskontrolle (gültig bis die Lerneinheit neu gelesen wird)
Leistungskontrolle als Semesterkurs
ECTS Kreditpunkte6 KP
PrüfendeG. Indiveri, E. Donati
Formbenotete Semesterleistung
PrüfungsspracheEnglisch
RepetitionRepetition nur nach erneuter Belegung der Lerneinheit möglich.
Zusatzinformation zum PrüfungsmodusRegistration modalities, date and venue of this performance assessment are specified solely by the UZH.

Lernmaterialien

Keine öffentlichen Lernmaterialien verfügbar.
Es werden nur die öffentlichen Lernmaterialien aufgeführt.

Gruppen

Keine Informationen zu Gruppen vorhanden.

Einschränkungen

Keine zusätzlichen Belegungseinschränkungen vorhanden.

Angeboten in

StudiengangBereichTyp
Neural Systems and Computation MasterWahlfächerWInformation
Neural Systems and Computation MasterNeurotechnologie und Neuromorphe IngenieurwissenschaftenWInformation