Training Spiking Deep Networks for Neuromorphic Hardware
arXiv:1611.05141 · doi:10.13140/RG.2.2.10967.06566
Abstract
We describe a method to train spiking deep networks that can be run using leaky integrate-and-fire (LIF) neurons, achieving state-of-the-art results for spiking LIF networks on five datasets, including the large ImageNet ILSVRC-2012 benchmark. Our method for transforming deep artificial neural networks into spiking networks is scalable and works with a wide range of neural nonlinearities. We achieve these results by softening the neural response function, such that its derivative remains bounded, and by training the network with noise to provide robustness against the variability introduced by spikes. Our analysis shows that implementations of these networks on neuromorphic hardware will be many times more power-efficient than the equivalent non-spiking networks on traditional hardware.
10 pages, 3 figures, 4 tables; the "methods" section of this article draws heavily on arXiv:1510.08829
Cited by in corpus (5)
- Efficient Computation in Adaptive Artificial Spiking Neural Networks
- Progressive Tandem Learning for Pattern Recognition with Deep Spiking Neural Networks
- Algorithm and Hardware Design of Discrete-Time Spiking Neural Networks Based on Back Propagation with Binary Activations
- Neuromorphic Processing and Sensing: Evolutionary Progression of AI to Spiking
- ST-MNIST -- The Spiking Tactile MNIST Neuromorphic Dataset