Learning and real-time classification of hand-written digits with spiking neural networks

TY - CHAP

T1 - Learning and real-time classification of hand-written digits with spiking neural networks

AU - Kulkarni, Shruti R.

AU - Alexiades, John M.

AU - Rajendran, Bipin

PY - 2018/2/14

Y1 - 2018/2/14

N2 - We describe a novel spiking neural network (SNN) for automated, real-time handwritten digit classification and its implementation on a GP-GPU platform. Information processing within the network, from feature extraction to classification is implemented by mimicking the basic aspects of neuronal spike initiation and propagation in the brain. The feature extraction layer of the SNN uses fixed synaptic weight maps to extract the key features of the image and the classifier layer uses the recently developed NormAD approximate gradient descent based supervised learning algorithm for spiking neural networks to adjust the synaptic weights. 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. We further use this network in a GPU based user-interface system demonstrating real-time SNN simulation to infer digits written by different users. On a test set of 500 such images, this real-time platform achieves an accuracy exceeding 97% while making a prediction within an SNN emulation time of less than 100 ms.

AB - We describe a novel spiking neural network (SNN) for automated, real-time handwritten digit classification and its implementation on a GP-GPU platform. Information processing within the network, from feature extraction to classification is implemented by mimicking the basic aspects of neuronal spike initiation and propagation in the brain. The feature extraction layer of the SNN uses fixed synaptic weight maps to extract the key features of the image and the classifier layer uses the recently developed NormAD approximate gradient descent based supervised learning algorithm for spiking neural networks to adjust the synaptic weights. 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. We further use this network in a GPU based user-interface system demonstrating real-time SNN simulation to infer digits written by different users. On a test set of 500 such images, this real-time platform achieves an accuracy exceeding 97% while making a prediction within an SNN emulation time of less than 100 ms.

KW - classification

KW - GPU based acceleration

KW - real-time processing

KW - Spiking neural networks

KW - supervised learning

UR - http://www.scopus.com/inward/record.url?scp=85047254951&partnerID=8YFLogxK

U2 - 10.1109/ICECS.2017.8292015

DO - 10.1109/ICECS.2017.8292015

M3 - Conference paper

AN - SCOPUS:85047254951

T3 - ICECS 2017 - 24th IEEE International Conference on Electronics, Circuits and Systems

SP - 128

EP - 131

BT - ICECS 2017 - 24th IEEE International Conference on Electronics, Circuits and Systems

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 24th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2017

Y2 - 5 December 2017 through 8 December 2017

ER -