Teaching pulsed integrated neural systems: a psychobiological approach
- 23 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10861947,p. 185-190
- https://doi.org/10.1109/mnnfs.1996.493790
Abstract
In this paper, we present a continuous time version of a differential Hebbian learning algorithm for pulsed neural systems with non-linear synapses. We argue that future analogue integrated implementations of artificial neural networks with on-chip learning must take as a starting point the basic properties of the technology. In particular asynchronous and inherently offset free, simple circuit structures must be used. We argue that unsupervised type learning schemes are most natural for analogue implementations and we seek inspiration from psychobiology to derive a learning scheme suitable for adaptive pulsed VLSI neural networks. We present simulations on this new learning scheme and show that it behaves as the original drive-reinforcement algorithm while being compatible with the technology. Finally, we show how the important weight change circuit is implemented in CMOS.Keywords
This publication has 13 references indexed in Scilit:
- On-chip learning in the analog domain with limited precision circuitsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- An analog feed-forward neural network with on-chip learningAnalog Integrated Circuits and Signal Processing, 1996
- Mixed analog/digital matrix-vector multiplier for neural network synapsesAnalog Integrated Circuits and Signal Processing, 1996
- An all-analog expandable neural network LSI with on-chip backpropagation learningIEEE Journal of Solid-State Circuits, 1994
- ErrataNeural Networks, 1994
- RECENT DEVELOPMENTS IN NEURODYNAMICS AND THEIR IMPACT ON THE DESIGN OF NEURO-CHIPSInternational Journal of Neural Systems, 1993
- A refreshable analog VLSI neural network chip with 400 neurons and 40 K synapsesIEEE Journal of Solid-State Circuits, 1992
- Weight perturbation: an optimal architecture and learning technique for analog VLSI feedforward and recurrent multilayer networksIEEE Transactions on Neural Networks, 1992
- Neuro chips with on-chip back-propagation and/or Hebbian learningIEEE Journal of Solid-State Circuits, 1992
- Pulse-stream VLSI neural networks mixing analog and digital techniquesIEEE Transactions on Neural Networks, 1991