In-Hardware Learning of Multilayer Spiking Neural Networks on a Neuromorphic Processor
This enables low-power, online learning for mobile applications using neuromorphic processors, though it is incremental in adapting existing methods to hardware constraints.
The paper tackled the problem of training spiking neural networks (SNNs) on neuromorphic hardware by developing a spike-based backpropagation algorithm with local update rules, achieving promising performance and energy-efficiency on datasets like MNIST and CIFAR-10.
Although widely used in machine learning, backpropagation cannot directly be applied to SNN training and is not feasible on a neuromorphic processor that emulates biological neuron and synapses. This work presents a spike-based backpropagation algorithm with biological plausible local update rules and adapts it to fit the constraint in a neuromorphic hardware. The algorithm is implemented on Intel Loihi chip enabling low power in-hardware supervised online learning of multilayered SNNs for mobile applications. We test this implementation on MNIST, Fashion-MNIST, CIFAR-10 and MSTAR datasets with promising performance and energy-efficiency, and demonstrate a possibility of incremental online learning with the implementation.