Spiking neural networks for handwritten digit recognition—Supervised learning and network optimization
Document Type
Article
Publication Date
7-1-2018
Abstract
We demonstrate supervised learning in Spiking Neural Networks (SNNs) for the problem of handwritten digit recognition using the spike triggered Normalized Approximate Descent (NormAD) algorithm. Our network that employs neurons operating at sparse biological spike rates below 300Hz achieves a classification accuracy of 98.17% on the MNIST test database with four times fewer parameters compared to the state-of-the-art. We present several insights from extensive numerical experiments regarding optimization of learning parameters and network configuration to improve its accuracy. We also describe a number of strategies to optimize the SNN for implementation in memory and energy constrained hardware, including approximations in computing the neuronal dynamics and reduced precision in storing the synaptic weights. Experiments reveal that even with 3-bit synaptic weights, the classification accuracy of the designed SNN does not degrade beyond 1% as compared to the floating-point baseline. Further, the proposed SNN, which is trained based on the precise spike timing information outperforms an equivalent non-spiking artificial neural network (ANN) trained using back propagation, especially at low bit precision. Thus, our study shows the potential for realizing efficient neuromorphic systems that use spike based information encoding and learning for real-world applications.
Identifier
85045477348 (Scopus)
Publication Title
Neural Networks
External Full Text Location
https://doi.org/10.1016/j.neunet.2018.03.019
e-ISSN
18792782
ISSN
08936080
PubMed ID
29674234
First Page
118
Last Page
127
Volume
103
Grant
2016-SD-2717
Fund Ref
Cisco Systems
Recommended Citation
Kulkarni, Shruti R. and Rajendran, Bipin, "Spiking neural networks for handwritten digit recognition—Supervised learning and network optimization" (2018). Faculty Publications. 8556.
https://digitalcommons.njit.edu/fac_pubs/8556
