Learning and Real-time Classification of Hand-written Digits With Spiking Neural Networks

no code implementations • 9 Nov 2017 • Shruti R. Kulkarni, John M. Alexiades, Bipin Rajendran

On the standard MNIST database images of handwritten digits, our network achieves an accuracy of 99. 80% on the training set and 98. 06% on the test set, with nearly 7x fewer parameters compared to the state-of-the-art spiking networks.

General Classification