VVZ API is not affiliated with ETH Zurich. Data might be outdated or incorrect. Please view the official ETHZ Vorlesungsverzeichnis for binding information.

402-0803-00L 6 Credits BSC , MSC D-HEST , D-MAVT , D-INFK , D-PHYS , D-ITET , D-MATH , D-BSSE

Neuromorphic Engineering I

Lecturers: Prof. em. Dr. Rodney J. Douglas, Prof. Dr. Giacomo Indiveri, PD Dr. Shih-Chii Liu, Prof. em. Dr. Tobias Delbrück
Examiners: Prof. Dr. Giacomo Indiveri, PD Dr. Shih-Chii Liu, Prof. em. Dr. Tobias Delbrück
VVZ CR n/a

Last Updated: 2026-02-05 15:24:51

Abstract

This course covers analog circuits with emphasis on neuromorphic engineering: MOS transistors in CMOS technology, static circuits, dynamic circuits, systems (silicon neuron, silicon retina, motion circuits) and an introduction to multi-chip systems. The lectures are accompanied by weekly laboratory sessions.

Objective

Understanding of the characteristics of neuromorphic circuit elements and their interaction in parallel networks.

Content

Neuromorphic analog circuits are inspired by the structure, function and plasticity of biological neurons and neural networks. Their computational primitives are based on electronic and optical properties of the physical structures in and on the semiconductor substrate. Neuromorphic algorithms typically rely on collective computation in parallel networks. Adaptation, learning and memory are implemented locally at each processing stage within the individual computational elements. Transistors are primarily 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. The high parallelism and connectivity of neuromorphic circuits permit structures with massive feedback without iterative methods and convergence problems and real-time processing networks for high-dimensional signals (e.g. images). Application domains of neuromorphic circuits include detailed real-time simulations of biological neurons and neural networks and the development of autonomous systems in robotics, vehicle guidance, and traffic control. This course covers elementary devices in CMOS and BiCMOS technology (MOS transistor below and above threshold, floating-gate MOS transistor, phototransducers), static circuits (differential pair, current mirror, transconductance amplifiers, multipliers, power-law circuits, resistive networks, etc.), dynamic circuits (linear and nonlinear filters, adaptive circuits), systems (silicon neuron, silicon retina, motion circuits) and an introduction to multi-chip systems. The lectures are accompanied by weekly laboratory sessions on the characterization of neuromorphic circuits, from elementary devices to entire systems.

Resources

Literature

S.-C. Liu et al.: Analog VLSI Circuits and Principles; various publications.

General Information

Language
English
Levels
BSC , MSC
Frequency
Yearly recurring

Examination

Type
session examination
Mode
oral 20 minutes

Course Components

Type Title Time & Place Hours
lecture Neuromorphic Engineering I
**gemeinsam mit der Uni Zürich**
  • Mon 13:00-14:45 (Y35 F 51)
2 h weekly
exercise Neuromorphic Engineering I
**gemeinsam mit der Uni Zürich**
  • By Appointment None-None
3 h weekly

Offered In