Skip to Main Content

Skip Nav Destination

Article navigation

September 01 2007

A Multichip Neuromorphic System for Spike-Based Visual Information Processing

In Special Collection: CogNet

R. Jacob Vogelstein,

R. Jacob Vogelstein

Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD 21205, U.S.A. jvogelst@jhu.edu

Search for other works by this author on:

Google Scholar

Udayan Mallik,

Udayan Mallik

Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD 21218, U.S.A. udayan@gmail.com

Search for other works by this author on:

Google Scholar

Eugenio Culurciello,

Eugenio Culurciello

Department of Electrical Engineering, Yale University, New Haven, CT 06511, U.S.A. eugenio.culurciello@yale.edu

Search for other works by this author on:

Google Scholar

Gert Cauwenberghs,

Gert Cauwenberghs

Division of Biological Sciences, University of California, San Diego, La Jolla, CA 92093, U.S.A. gert@ucsd.edu

Search for other works by this author on:

Google Scholar

Ralph Etienne-Cummings

Ralph Etienne-Cummings

Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD 21218, U.S.A. retienne@jhu.edu

Search for other works by this author on:

Google Scholar

Author and Article Information

R. Jacob Vogelstein

Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD 21205, U.S.A. jvogelst@jhu.edu

Udayan Mallik

Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD 21218, U.S.A. udayan@gmail.com

Eugenio Culurciello

Department of Electrical Engineering, Yale University, New Haven, CT 06511, U.S.A. eugenio.culurciello@yale.edu

Gert Cauwenberghs

Division of Biological Sciences, University of California, San Diego, La Jolla, CA 92093, U.S.A. gert@ucsd.edu

Ralph Etienne-Cummings

Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD 21218, U.S.A. retienne@jhu.edu

Received: March 29 2006

Accepted: October 07 2006

Online ISSN: 1530-888X

Print ISSN: 0899-7667

© 2007 Massachusetts Institute of Technology

2007

Neural Computation (2007) 19 (9): 2281–2300.

https://doi.org/10.1162/neco.2007.19.9.2281

Abstract

We present a multichip, mixed-signal VLSI system for spike-based vision processing. The system consists of an 80 × 60 pixel neuromorphic retina and a 4800 neuron silicon cortex with 4,194,304 synapses. Its functionality is illustrated with experimental data on multiple components of an attention-based hierarchical model of cortical object recognition, including feature coding, salience detection, and foveation. This model exploits arbitrary and reconfigurable connectivity between cells in the multichip architecture, achieved by asynchronously routing neural spike events within and between chips according to a memory-based look-up table. Synaptic parameters, including conductance and reversal potential, are also stored in memory and are used to dynamically configure synapse circuits within the silicon neurons.

This content is only available as a PDF.

© 2007 Massachusetts Institute of Technology

2007

You do not currently have access to this content.

Don't already have an account? Register

You could not be signed in. Please check your email address / username and password and try again.