Training Spiking Deep Networks for Neuromorphic Hardware
This enables more power-efficient AI implementations on neuromorphic hardware, though it is incremental as it builds on existing spiking network methods.
The paper tackles the problem of training spiking deep networks for neuromorphic hardware, achieving state-of-the-art results on five datasets including ImageNet ILSVRC-2012 by softening neural response functions and using noise training.
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.