Stochasticity and Robustness in Spiking Neural Networks
This addresses robustness issues in neuromorphic hardware for researchers and engineers, but it is incremental as it builds on existing spiking neuron models.
The paper tackles the problem of synaptic inaccuracy in spiking neural networks by showing that noise can enhance robustness, with noisy networks tolerating inaccuracies from hafnium-oxide resistive memory.
Artificial neural networks normally require precise weights to operate, despite their origins in biological systems, which can be highly variable and noisy. When implementing artificial networks which utilize analog 'synaptic' devices to encode weights, however, inherent limits are placed on the accuracy and precision with which these values can be encoded. In this work, we investigate the effects that inaccurate synapses have on spiking neurons and spiking neural networks. Starting with a mathematical analysis of integrate-and-fire (IF) neurons, including different non-idealities (such as leakage and channel noise), we demonstrate that noise can be used to make the behavior of IF neurons more robust to synaptic inaccuracy. We then train spiking networks which utilize IF neurons with and without noise and leakage, and experimentally confirm that the noisy networks are more robust. Lastly, we show that a noisy network can tolerate the inaccuracy expected when hafnium-oxide based resistive random-access memory is used to encode synaptic weights.