Spike Event Based Learning in Neural Networks
This provides a method for transferring ideas between deep learning and computational neuroscience, but it appears incremental as it builds on existing spiking neural network concepts.
The paper tackles learning connectivity in spiking neural networks by deriving a scheme with online, local rules applied only during spike events, and demonstrates it on a self-supervised prediction and classification task for moving MNIST images using a Dynamic Vision Sensor.
A scheme is derived for learning connectivity in spiking neural networks. The scheme learns instantaneous firing rates that are conditional on the activity in other parts of the network. The scheme is independent of the choice of neuron dynamics or activation function, and network architecture. It involves two simple, online, local learning rules that are applied only in response to occurrences of spike events. This scheme provides a direct method for transferring ideas between the fields of deep learning and computational neuroscience. This learning scheme is demonstrated using a layered feedforward spiking neural network trained self-supervised on a prediction and classification task for moving MNIST images collected using a Dynamic Vision Sensor.