A Deep Unsupervised Feature Learning Spiking Neural Network with Binarized Classification Layers for EMNIST Classification using SpykeFlow
This work addresses the need for low-power AI on IoT devices, though it is incremental as it combines existing methods like STDP and gradient descent in a hybrid approach.
The paper tackles the problem of energy-efficient deep learning for edge devices by proposing a spiking neural network that uses unsupervised STDP for feature extraction and gradient descent only on the output layer for classification on the EMNIST dataset, achieving competitive accuracies.
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.