Competitive Maximization of Neuronal Activity in Convolutional Recurrent Spiking Neural Networks

Nekhaev, Dmitry; Демин, В. А.

doi:10.1007/978-3-030-30425-6_30

Cited by 1 publication

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Demin and Nekhaev ( 2018 ) proposed a bio-inspired learning rule FEELING with an attempt on the recurrent structure, which is applied to the handwritten digit recognition. The FEELING algorithm was further implemented by Nekhaev and Demin ( 2020 ) with an convolutional recurrent structure that has been proven to be more energy efficient on hand digit recognition. However, this work did not consider the research line where the combination of convolutional and recurrent structure is more significant in a dynamic scene based recognition (i.e., hand gesture recognition).…”

Section: Introductionmentioning

confidence: 99%

A New Spiking Convolutional Recurrent Neural Network (SCRNN) With Applications to Event-Based Hand Gesture Recognition

2020

View full text Add to dashboard Cite

The combination of neuromorphic visual sensors and spiking neural network offers a high efficient bio-inspired solution to real-world applications. However, processing event- based sequences remains challenging because of the nature of their asynchronism and sparsity behavior. In this paper, a novel spiking convolutional recurrent neural network (SCRNN) architecture that takes advantage of both convolution operation and recurrent connectivity to maintain the spatial and temporal relations from event-based sequence data are presented. The use of recurrent architecture enables the network to have a sampling window with an arbitrary length, allowing the network to exploit temporal correlations between event collections. Rather than standard ANN to SNN conversion techniques, the network utilizes a supervised Spike Layer Error Reassignment (SLAYER) training mechanism that allows the network to adapt to neuromorphic (event-based) data directly. The network structure is validated on the DVS gesture dataset and achieves a 10 class gesture recognition accuracy of 96.59% and an 11 class gesture recognition accuracy of 90.28%.

show abstract

Section: Introductionmentioning

confidence: 99%