Spiking Deep Convolutional Neural Networks for Energy-Efficient Object Recognition

• Published in: International journal of computer vision Vol. 113; no. 1; pp. 54 - 66
• Main Authors: Cao, Yongqiang, Chen, Yang, Khosla, Deepak
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.05.2015; Springer; Springer Nature B.V
• Subjects: Analysis; Artificial Intelligence; Back propagation; Circuits; Computer Imaging; Computer Science; Deep learning; Energy efficiency; Energy management systems; Energy use; Hardware; Image Processing and Computer Vision; Laboratories; Machine learning; Mapping; Mathematical models; Neural networks; Object recognition; Pattern Recognition; Pattern Recognition and Graphics; Power; Power consumption; Spiking; Studies; Towers; Trains; Vision; Vision systems; Deep learning; Neuromorphic circuits; Convolutional neural networks; Object recognition; Machine learning; Spiking neural networks
• ISSN: 0920-5691; 1573-1405
• DOI: 10.1007/s11263-014-0788-3

Deep-learning neural networks such as convolutional neural network (CNN) have shown great potential as a solution for difficult vision problems, such as object recognition. Spiking neural networks (SNN)-based architectures have shown great potential as a solution for realizing ultra-low power consumption using spike-based neuromorphic hardware. This work describes a novel approach for converting a deep CNN into a SNN that enables mapping CNN to spike-based hardware architectures. Our approach first tailors the CNN architecture to fit the requirements of SNN, then trains the tailored CNN in the same way as one would with CNN, and finally applies the learned network weights to an SNN architecture derived from the tailored CNN. We evaluate the resulting SNN on publicly available Defense Advanced Research Projects Agency (DARPA) Neovision2 Tower and CIFAR-10 datasets and show similar object recognition accuracy as the original CNN. Our SNN implementation is amenable to direct mapping to spike-based neuromorphic hardware, such as the ones being developed under the DARPA SyNAPSE program. Our hardware mapping analysis suggests that SNN implementation on such spike-based hardware is two orders of magnitude more energy-efficient than the original CNN implementation on off-the-shelf FPGA-based hardware.