A Gradient Estimator for Time-Varying Electrical Networks with Non-Linear Dissipation

Abstract

We propose a method for extending the technique of equilibrium propagation for estimating gradients in fixed-point neural networks to the more general setting of directed, time-varying neural networks by modeling them as electrical circuits. We use electrical circuit theory to construct a Lagrangian capable of describing deep, directed neural networks modeled using nonlinear capacitors and inductors, linear resistors and sources, and a special class of nonlinear dissipative elements called fractional memristors. We then derive an estimator for the gradient of the physical parameters of the network, such as synapse conductances, with respect to an arbitrary loss function. This estimator is entirely local, in that it only depends on information locally available to each synapse. We conclude by suggesting methods for extending these results to networks of biologically plausible neurons, e.g. Hodgkin-Huxley neurons.

12 pages, 0 figures

References in corpus (5)

• Playing Atari with Deep Reinforcement Learning
• The classical mechanics of non-conservative systems
• The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Sharp Minima and Regularization Effects
• On the loss landscape of a class of deep neural networks with no bad local valleys
• Training End-to-End Analog Neural Networks with Equilibrium Propagation

Cited by in corpus (1)

• A deep learning theory for neural networks grounded in physics