A Deep Unsupervised Feature Learning Spiking Neural Network With Binarized Classification Layers for the EMNIST Classification

Abstract

End user AI is trained on large server farms with data collected from the users. With ever increasing demand for IoT devices, there is a need for deep learning approaches that can be implemented at the Edge in an energy efficient manner. In this work we approach this using spiking neural networks. The unsupervised learning technique of spike timing dependent plasticity (STDP) and binary activations are used to extract features from spiking input data. Gradient descent (backpropagation) is used only on the output layer to perform training for classification. The accuracies obtained for the balanced <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">EMNIST</small> data set compare favorably with other approaches. The effect of the stochastic gradient descent (SGD) approximations on learning capabilities of our network are also explored.