TechRxiv
IJCNN_2020__Finalmanuscript.pdf (3.79 MB)

Training of a Spiking Neural Network on spintronics based analog hardware for handwritten digit recognition

Download (3.79 MB)
preprint
posted on 11.06.2021, 04:11 by Upasana Sahu, Kushaagra Goyal, Debanjan Bhowmik
We trained Spiking neural network (SNN) using spike time dependent plasticity (STDP)-enabled learning under two different learning schemes in MNIST data set(hand written digit recognition). We showed how the post-neurons need to be far more in number than the output classes for larger data sets in the case of SNN for reasonably high accuracy number. We have also reported the net energy consumed for learning in the spintronic devices and associated transistor-based circuits that enable synaptic functionality for this SNN.

History

Email Address of Submitting Author

upasanasahu06@gmail.com

Submitting Author's Institution

Indian Institute of Technology Delhi

Submitting Author's Country

India