Feedforward Categorization on AER Motion Events Using Cortex-Like Features in a Spiking Neural Network

• Published in: IEEE transaction on neural networks and learning systems Vol. 26; no. 9; pp. 1963 - 1978
• Main Authors: Bo Zhao, Ruoxi Ding, Shoushun Chen, Linares-Barranco, Bernabe, Huajin Tang
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.09.2015; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Action Potentials - physiology; Address event representation (AER); Cerebral Cortex - cytology; Computer architecture; Convolution; Datasets; event driven; Feature extraction; feedforward categorization; Feedforward neural networks; Humans; Kernel; MNIST; Models, Neurological; Motion; Nerve Net - physiology; Neural Networks (Computer); Neurons; Neurons - physiology; Sensors; spiking neural network; Vision systems; Visualization; MNIST; Address event representation (AER); feedforward categorization; event driven; spiking neural network
• ISSN: 2162-237X; 2162-2388; 2162-2388
• DOI: 10.1109/TNNLS.2014.2362542

This paper introduces an event-driven feedforward categorization system, which takes data from a temporal contrast address event representation (AER) sensor. The proposed system extracts bio-inspired cortex-like features and discriminates different patterns using an AER based tempotron classifier (a network of leaky integrate-and-fire spiking neurons). One of the system's most appealing characteristics is its event-driven processing, with both input and features taking the form of address events (spikes). The system was evaluated on an AER posture dataset and compared with two recently developed bio-inspired models. Experimental results have shown that it consumes much less simulation time while still maintaining comparable performance. In addition, experiments on the Mixed National Institute of Standards and Technology (MNIST) image dataset have demonstrated that the proposed system can work not only on raw AER data but also on images (with a preprocessing step to convert images into AER events) and that it can maintain competitive accuracy even when noise is added. The system was further evaluated on the MNIST dynamic vision sensor dataset (in which data is recorded using an AER dynamic vision sensor), with testing accuracy of 88.14%.