An Approximate Backpropagation Learning Rule for Memristor Based Neural Networks Using Synaptic Plasticity
Neural and Evolutionary Computing
2016-07-28 v2 Emerging Technologies
Abstract
We describe an approximation to backpropagation algorithm for training deep neural networks, which is designed to work with synapses implemented with memristors. The key idea is to represent the values of both the input signal and the backpropagated delta value with a series of pulses that trigger multiple positive or negative updates of the synaptic weight, and to use the min operation instead of the product of the two signals. In computational simulations, we show that the proposed approximation to backpropagation is well converged and may be suitable for memristor implementations of multilayer neural networks.
Cite
@article{arxiv.1511.07076,
title = {An Approximate Backpropagation Learning Rule for Memristor Based Neural Networks Using Synaptic Plasticity},
author = {D. V. Negrov and I. M. Karandashev and V. V. Shakirov and Yu. A. Matveyev and W. L. Dunin-Barkowski and A. V. Zenkevich},
journal= {arXiv preprint arXiv:1511.07076},
year = {2016}
}
Comments
21 pages, 6 figures, 1 table, title changed, manuscript thoroughly rewritten