A VLSI Implementation of an Analog Neural Network Suited for Genetic Algorithms

Authors:
Johannes Schemmel;Karlheinz Meier;Felix Schürmann
Affiliations:
-;-;-
Venue:
ICES '01 Proceedings of the 4th International Conference on Evolvable Systems: From Biology to Hardware
Year:
2001

Citing 2
Cited 4

Array-Based Analog Computation

IEEE Micro
Towards a Silicon Primordial Soup: A Fast Approach to Hardware Evolution with a VLSI Transistor Array

ICES '00 Proceedings of the Third International Conference on Evolvable Systems: From Biology to Hardware

A Mixed-Mode Analog Neural Network Using Current-Steering Synapses

Analog Integrated Circuits and Signal Processing
Intrinsic and extrinsic implementation of a bio-inspired hardware system

Information Sciences—Informatics and Computer Science: An International Journal - Special issue: Bio-inspired systems (BIS)
A neural simulation system based on biologically realistic electronic neurons

Information Sciences—Informatics and Computer Science: An International Journal - Special issue: Bio-inspired systems (BIS)
Investigating the Suitability of FPAAs for Evolved Hardware Spiking Neural Networks

ICES '08 Proceedings of the 8th international conference on Evolvable Systems: From Biology to Hardware

Quantified Score

Hi-index	0.00

Visualization

Abstract

The usefulness of an artificial analog neural network is closely bound to its trainability. This paper introduces a new analog neural network architecture using weights determined by a genetic algorithm. The first VLSI implementation presented in this paper achieves 200 giga connections per second with 4096synapses on less than 1 mm2 silicon area. Since the training can be done at the full speed of the network, several hundred individuals per second can be tested by the genetic algorithm. This makes it feasible to tackle problems that require large multi-layered networks.