A Deep Unsupervised Feature Learning Spiking Neural Network with Binarized Classification Layers for EMNIST Classification using SpykeFlow

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) using binary activations are used to extract features from spiking input data. Gradient descent (backpropagation) is used only on the output layer to perform the training for classification. The accuracies obtained for the balanced EMNIST data set compare favorably with other approaches. The effect of stochastic gradient descent (SGD) approximations on learning capabilities of our network are also explored.

arXiv commentA section of of this work is Submitted to IEEE TETCI 2020 Journal

References in corpus (13)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• The NumPy array: a structure for efficient numerical computation
• Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
• STDP-based spiking deep convolutional neural networks for object recognition
• EMNIST: an extension of MNIST to handwritten letters
• A CMOS Spiking Neuron for Brain-Inspired Neural Networks with Resistive Synapses and In-Situ Learning
• Bio-inspired Unsupervised Learning of Visual Features Leads to Robust Invariant Object Recognition
• SpykeTorch: Efficient Simulation of Convolutional Spiking Neural Networks with at most one Spike per Neuron
• Theory and Tools for the Conversion of Analog to Spiking Convolutional Neural Networks
• Homogeneous Spiking Neuromorphic System for Real-World Pattern Recognition
• Supervised Learning in Spiking Neural Networks for Precise Temporal Encoding
• Dendritic-Inspired Processing Enables Bio-Plausible STDP in Compound Binary Synapses
• Towards Scalable, Efficient and Accurate Deep Spiking Neural Networks with Backward Residual Connections, Stochastic Softmax and Hybridization