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

arXiv: https://arxiv.org/abs/2002.11843 · HTML: https://mlsanity.com/paper/2002.11843/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Feb 2020.

## Built on by (most cited first, 2 of 2)

- [STSC-SNN: Spatio-Temporal Synaptic Connection with Temporal Convolution and Attention for Spiking Neural Networks](https://mlsanity.com/paper/2210.05241/) (2022)
- [Neuromorphic Event-Driven Semantic Communication in Microgrids](https://mlsanity.com/paper/2402.18390/) (2024)

## Abstract (arXiv)

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.