Stochastic Synapses Enable Efficient Brain-Inspired Learning Machines

TL;DR

This paper introduces Synaptic Sampling Machines, neural networks that leverage synaptic stochasticity for efficient sampling and learning, demonstrating robustness, sparsity, and superior performance in spike-based models for brain-inspired hardware applications.

Contribution

The paper presents a novel class of neural networks using synaptic unreliability for sampling and learning, with a local plasticity rule enabling online training and robustness to pruning.

Findings

Perform well with discrete or continuous neurons.

Learn sparse, robust representations.

Outperform existing spike-based learners.

Abstract

Recent studies have shown that synaptic unreliability is a robust and sufficient mechanism for inducing the stochasticity observed in cortex. Here, we introduce Synaptic Sampling Machines, a class of neural network models that uses synaptic stochasticity as a means to Monte Carlo sampling and unsupervised learning. Similar to the original formulation of Boltzmann machines, these models can be viewed as a stochastic counterpart of Hopfield networks, but where stochasticity is induced by a random mask over the connections. Synaptic stochasticity plays the dual role of an efficient mechanism for sampling, and a regularizer during learning akin to DropConnect. A local synaptic plasticity rule implementing an event-driven form of contrastive divergence enables the learning of generative models in an on-line fashion. Synaptic sampling machines perform equally well using discrete-timed artificial units (as in Hopfield networks) or continuous-timed leaky integrate & fire neurons. The learned representations are remarkably sparse and robust to reductions in bit precision and synapse pruning: removal of more than 75% of the weakest connections followed by cursory re-learning causes a negligible performance loss on benchmark classification tasks. The spiking neuron-based synaptic sampling machines outperform existing spike-based unsupervised learners, while potentially offering substantial advantages in terms of power and complexity, and are thus promising models for on-line learning in brain-inspired hardware.