Semantic Scholar Open Access 2018 1174 sitasi

Going Deeper in Spiking Neural Networks: VGG and Residual Architectures

Abhronil Sengupta Yuting Ye Robert Y. Wang Chiao Liu K. Roy

Abstrak

Over the past few years, Spiking Neural Networks (SNNs) have become popular as a possible pathway to enable low-power event-driven neuromorphic hardware. However, their application in machine learning have largely been limited to very shallow neural network architectures for simple problems. In this paper, we propose a novel algorithmic technique for generating an SNN with a deep architecture, and demonstrate its effectiveness on complex visual recognition problems such as CIFAR-10 and ImageNet. Our technique applies to both VGG and Residual network architectures, with significantly better accuracy than the state-of-the-art. Finally, we present analysis of the sparse event-driven computations to demonstrate reduced hardware overhead when operating in the spiking domain.

Penulis (5)

A

Abhronil Sengupta

Y

Yuting Ye

R

Robert Y. Wang

C

Chiao Liu

K

K. Roy

Format Sitasi

Sengupta, A., Ye, Y., Wang, R.Y., Liu, C., Roy, K. (2018). Going Deeper in Spiking Neural Networks: VGG and Residual Architectures. https://doi.org/10.3389/fnins.2019.00095

Akses Cepat

Lihat di Sumber doi.org/10.3389/fnins.2019.00095
Informasi Jurnal
Tahun Terbit
2018
Bahasa
en
Total Sitasi
1174×
Sumber Database
Semantic Scholar
DOI
10.3389/fnins.2019.00095
Akses
Open Access ✓