Modular analog continuous-time VLSI neural networks with on-chip Hebbian learning and analog storage
- 2 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 1533-1536
- https://doi.org/10.1109/iscas.1992.230207
Abstract
A modular analog circuit design approach for hardware implementations of neural networks is presented. This approach is based on the use of small transconductance multipliers as the main component, and is therefore called the T-mode (transconductance-mode) approach. This circuit design technique was used to design a set of modular chips which assembled to build either BAM (bidirectional associative memory) networks, Hopfield networks, winner-take-all networks, or simplified ART1 networks. The approach is extended afterwards in order to include a Hebbian learning rule into each synapse. As an example, a learning BAM network system is shown. The experimental results given were obtained from 2- mu m CMOS double-metal double-polysilicon (MOSIS) prototypes.Keywords
This publication has 20 references indexed in Scilit:
- A massively parallel architecture for a self-organizing neural pattern recognition machinePublished by Elsevier ,2005
- A modular T-mode design approach for analog neural network hardware implementationsIEEE Journal of Solid-State Circuits, 1992
- A 336-neuron, 28 K-synapse, self-learning neural network chip with branch-neuron-unit architectureIEEE Journal of Solid-State Circuits, 1991
- Pulse-stream VLSI neural networks mixing analog and digital techniquesIEEE Transactions on Neural Networks, 1991
- VLSI implementation of ART1 memoriesIEEE Transactions on Neural Networks, 1991
- Neuromorphic electronic systemsProceedings of the IEEE, 1990
- Bidirectional associative memoriesIEEE Transactions on Systems, Man, and Cybernetics, 1988
- Adaptive bidirectional associative memoriesApplied Optics, 1987
- Learning representations by back-propagating errorsNature, 1986
- Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuitIEEE Transactions on Circuits and Systems, 1986