A Caltech Library Service

A Learning Analog Neural Network Chip with Continuous-Time Recurrent Dynamics

Cauwenberghs, Gert (1994) A Learning Analog Neural Network Chip with Continuous-Time Recurrent Dynamics. In: Advances in Neural Information Processing Systems 6. Morgan Kaufmann , San Francisco, CA. ISBN 1-55860-322-0.

[img] PDF - Published Version
See Usage Policy.


Use this Persistent URL to link to this item:


We present experimental results on supervised learning of dynamical features in an analog VLSI neural network chip. The recurrent network, containing six continuous-time analog neurons and 42 free parameters (connection strengths and thresholds), is trained to generate time-varying outputs approximating given periodic signals presented to the network. The chip implements a stochastic perturbative algorithm, which observes the error gradient along random directions in the parameter space for error-descent learning. In addition to the integrated learning functions and the generation of pseudo-random perturbations, the chip provides for teacher forcing and long-term storage of the volatile parameters. The network learns a 1 kHz circular trajectory in 100 sec. The chip occupies 2mm x 2mm in a 2μm CMOS process, and dissipates 1.2 m W.

Item Type:Book Section
Additional Information:© 1994 Morgan Kaufmann. Fabrication of the CMOS chip was provided through the DARPA/NSF MOSIS service. Financial support by the NIPS Foundation largely covered the expenses of attending the conference.
Funding AgencyGrant Number
Record Number:CaltechAUTHORS:20150305-163505478
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:55570
Deposited By: Kristin Buxton
Deposited On:06 Mar 2015 05:19
Last Modified:03 Oct 2019 08:06

Repository Staff Only: item control page