Welcome to the InfoSci Platform
Reference Hub5
An Event-Based Neural Network Architecture with Content Addressable Memory

An Event-Based Neural Network Architecture with Content Addressable Memory

Sivaganesan S, Maria Antony S, Udayakumar E
Copyright: © 2020 |Volume: 11 |Issue: 1 |Pages: 18
ISSN: 1947-3176|EISSN: 1947-3184|EISBN13: 9781799806998|DOI: 10.4018/IJERTCS.2020010102
Cite Article Cite Article

MLA

Sivaganesan S, et al. "An Event-Based Neural Network Architecture with Content Addressable Memory." IJERTCS vol.11, no.1 2020: pp.23-40. http://doi.org/10.4018/IJERTCS.2020010102

APA

Sivaganesan S, Maria Antony S, & Udayakumar E. (2020). An Event-Based Neural Network Architecture with Content Addressable Memory. International Journal of Embedded and Real-Time Communication Systems (IJERTCS), 11(1), 23-40. http://doi.org/10.4018/IJERTCS.2020010102

Chicago

Sivaganesan S, Maria Antony S, and Udayakumar E. "An Event-Based Neural Network Architecture with Content Addressable Memory," International Journal of Embedded and Real-Time Communication Systems (IJERTCS) 11, no.1: 23-40. http://doi.org/10.4018/IJERTCS.2020010102

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

A hybrid analog/digital very large-scale integration (VLSI) implementation of a spiking neural network with programmable synaptic weights was designed. The synaptic weight values are stored in an asynchronous module, which is interfaced to a fast current-mode event-driven DAC for producing synaptic currents with the appropriate amplitude values. It acts as a transceiver, receiving asynchronous events for input, performing neural computations with hybrid analog/digital circuits on the input spikes, and eventually producing digital asynchronous events in output. Input, output, and synaptic weight values are transmitted to/from the chip using a common communication protocol based on the address event representation (AER). Using this representation, it is possible to interface the device to a workstation or a microcontroller and explore the effect of different types of spike-timing dependent plasticity (STDP) learning algorithms for updating the synaptic weights values in the CAM module.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.