Giacomo Indiveri: Catalogue data in Autumn Semester 2020

Name Prof. Dr. Giacomo Indiveri
FieldNeuromorphic Cognitive Systems
Address
Universität Zürich
Winterthurerstr. 190
Neuroinformatik
8057 Zürich
SWITZERLAND
Telephone044 635 30 39
E-mailgiacomo@ethz.ch
URLhttps://www.ini.uzh.ch/en/institute/people?uname=giacomo
DepartmentInformation Technology and Electrical Engineering
RelationshipAssociate Professor

NumberTitleECTSHoursLecturers
227-0085-09LProjects & Seminars: Spiking Neural Network on Neuromorphic processors Restricted registration - show details
Only for Electrical Engineering and Information Technology BSc.

The course unit can only be taken once. Repeated enrollment in a later semester is not creditable.
3 credits3PG. Indiveri
AbstractThe category of "Laboratory Courses, Projects, Seminars" includes courses and laboratories in various formats designed to impart practical knowledge and skills. Moreover, these classes encourage independent experimentation and design, allow for explorative learning and teach the methodology of project work.
ObjectiveMachine Learning – Spiking Neural Network – DVS Cameras - Programming Neuromoripch processors – Intel Loihi - Final Project with a presentation.

Compared to the “traditional” artificial neural network, the spiking neural network (SNN) can provided both latency and energy efficiency. Moreover, SNN has demonstrated in previous works a better performance in processing physiological information of small sample size, and only the output layer of the spiking neural network needs to be trained, which results in a fast training rate. This couse focuses on giving the bases of spiking neural networks and neuromorphic processors. Students will learn the tools to implement SNN algorithm in both academic processors and Intel Loihi using data from Event-based Vision camera and biomedical sensors (i.e. ECG and EEG). The course will end with 4 weeks project
where the students can target a specif application scenario.

The course will be taught in English.
227-1031-00LJournal Club (University of Zurich)
No enrolment to this course at ETH Zurich. Book the corresponding module directly at UZH.
UZH Module Code: INI702

Mind the enrolment deadlines at UZH:
Link
2 credits1SG. Indiveri
AbstractThe Neuroinformatics Journal club is a weekly meeting during which students present current research papers.
The presentation last from 30 to 60 Minutes and is followed by a general discussion.
ObjectiveThe Neuroinformatics Journal club aims to train students to present cutting-edge research clealry and efficiently. It leads students to learn about current topics in neurosciences and neuroinformatics, to search the relevant literature and to critically and scholarly appraise published papers. The students learn to present complex concepts and answer critical questions.
ContentRelevant current papers in neurosciences and neuroinformatics are covered.
227-1033-00LNeuromorphic Engineering I Information Restricted registration - show details
Registration in this class requires the permission of the instructors. Class size will be limited to available lab spots.
Preference is given to students that require this class as part of their major.

Information for UZH students:
Enrolment to this course unit only possible at ETH. No enrolment to module INI404 at UZH.
Please mind the ETH enrolment deadlines for UZH students: Link
6 credits2V + 3UT. Delbrück, G. Indiveri, S.‑C. Liu
AbstractThis course covers analog circuits with emphasis on neuromorphic engineering: MOS transistors in CMOS technology, static circuits, dynamic circuits, systems (silicon neuron, silicon retina, silicon cochlea) with an introduction to multi-chip systems. The lectures are accompanied by weekly laboratory sessions.
ObjectiveUnderstanding of the characteristics of neuromorphic circuit elements.
ContentNeuromorphic circuits are inspired by the organizing principles of biological neural circuits. Their computational primitives are based on physics of semiconductor devices. Neuromorphic architectures often rely on collective computation in parallel networks. Adaptation, learning and memory are implemented locally within the individual computational elements. Transistors are often operated in weak inversion (below threshold), where they exhibit exponential I-V characteristics and low currents. These properties lead to the feasibility of high-density, low-power implementations of functions that are computationally intensive in other paradigms. Application domains of neuromorphic circuits include silicon retinas and cochleas for machine vision and audition, real-time emulations of networks of biological neurons, and the development of autonomous robotic systems. This course covers devices in CMOS technology (MOS transistor below and above threshold, floating-gate MOS transistor, phototransducers), static circuits (differential pair, current mirror, transconductance amplifiers, etc.), dynamic circuits (linear and nonlinear filters, adaptive circuits), systems (silicon neuron, silicon retina and cochlea) and an introduction to multi-chip systems that communicate events analogous to spikes. The lectures are accompanied by weekly laboratory sessions on the characterization of neuromorphic circuits, from elementary devices to systems.
LiteratureS.-C. Liu et al.: Analog VLSI Circuits and Principles; various publications.
Prerequisites / NoticeParticular: The course is highly recommended for those who intend to take the spring semester course 'Neuromorphic Engineering II', that teaches the conception, simulation, and physical layout of such circuits with chip design tools.

Prerequisites: Background in basics of semiconductor physics helpful, but not required.
227-1037-00LIntroduction to Neuroinformatics Information 6 credits2V + 1UV. Mante, M. Cook, B. Grewe, G. Indiveri, D. Kiper, W. von der Behrens
AbstractThe course provides an introduction to the functional properties of neurons. Particularly the description of membrane electrical properties (action potentials, channels), neuronal anatomy, synaptic structures, and neuronal networks. Simple models of computation, learning, and behavior will be explained. Some artificial systems (robot, chip) are presented.
ObjectiveUnderstanding computation by neurons and neuronal circuits is one of the great challenges of science. Many different disciplines can contribute their tools and concepts to solving mysteries of neural computation. The goal of this introductory course is to introduce the monocultures of physics, maths, computer science, engineering, biology, psychology, and even philosophy and history, to discover the enchantments and challenges that we all face in taking on this major 21st century problem and how each discipline can contribute to discovering solutions.
ContentThis course considers the structure and function of biological neural networks at different levels. The function of neural networks lies fundamentally in their wiring and in the electro-chemical properties of nerve cell membranes. Thus, the biological structure of the nerve cell needs to be understood if biologically-realistic models are to be constructed. These simpler models are used to estimate the electrical current flow through dendritic cables and explore how a more complex geometry of neurons influences this current flow. The active properties of nerves are studied to understand both sensory transduction and the generation and transmission of nerve impulses along axons. The concept of local neuronal circuits arises in the context of the rules governing the formation of nerve connections and topographic projections within the nervous system. Communication between neurons in the network can be thought of as information flow across synapses, which can be modified by experience. We need an understanding of the action of inhibitory and excitatory neurotransmitters and neuromodulators, so that the dynamics and logic of synapses can be interpreted. Finally, the neural architectures of feedforward and recurrent networks will be discussed in the context of co-ordination, control, and integration of sensory and motor information in neural networks.
227-1039-00LBasics of Instrumentation, Measurement, and Analysis (University of Zurich) Restricted registration - show details
No enrolment to this course at ETH Zurich. Book the corresponding module directly at UZH.
UZH Module Code: INI502

Mind the enrolment deadlines at UZH:
Link

Registration in this class requires the permission of the instructors. Class size will be limited to available lab spots.
Preference is given to students that require this class as part of their major.
4 credits9SS.‑C. Liu, T. Delbrück, R. Hahnloser, G. Indiveri, V. Mante, P. Pyk, D. Scaramuzza, W. von der Behrens
AbstractExperimental data are always as good as the instrumentation and measurement, but never any better. This course provides the very basics of instrumentation relevant to neurophysiology and neuromorphic engineering, it consists of two parts: a common introductory part involving analog signals and their acquisition (Part I), and a more specialized second part (Part II).
ObjectiveThe goal of Part I is to provide a general introduction to the signal acquisition process. Students are familiarized with basic lab equipment such as oscilloscopes, function generators, and data acquisition devices. Different electrical signals are generated, visualized, filtered, digitized, and analyzed using Matlab (Mathworks Inc.) or Labview (National Instruments).

In Part II, the students are divided into small groups to work on individual measurement projects according to availability and interest. Students single-handedly solve a measurement task, making use of their basic knowledge acquired in the first part. Various signal sources will be provided.
Prerequisites / NoticeFor each part, students must hand in a written report and present a live demonstration of their measurement setup to the respective supervisor. The supervisor of Part I is the teaching assistant, and the supervisor of Part II is task specific. Admission to Part II is conditional on completion of Part I (report + live demonstration).

Reports must contain detailed descriptions of the measurement goal, the measurement procedure, and the measurement outcome. Either confidence or significance of measurements must be provided. Acquisition and analysis software must be documented.