Back to Search
Start Over
Stochastic Synapses Enable Efficient Brain-Inspired Learning Machines
- Source :
- Frontiers in Neuroscience 10 (2016): 241
- Publication Year :
- 2015
-
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.
- Subjects :
- Computer Science - Neural and Evolutionary Computing
Subjects
Details
- Database :
- arXiv
- Journal :
- Frontiers in Neuroscience 10 (2016): 241
- Publication Type :
- Report
- Accession number :
- edsarx.1511.04484
- Document Type :
- Working Paper
- Full Text :
- https://doi.org/10.3389/fnins.2016.00241