Bio-inspired categorization using event-driven feature extraction and spike-based learning

• Main Authors: Zhao, Bo, Chen, Shoushun, Tang, Huajin
• 其他作者: School of Electrical and Electronic Engineering
• 格式: Conference or Workshop Item
• 語言: English
• 出版: 2014
• 主題: DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems
• 在線閱讀: https://hdl.handle.net/10356/103456; http://hdl.handle.net/10220/24499

This paper presents a fully event-driven feedforward architecture that accounts for rapid categorization. The proposed algorithm processes the address event data generated either from an image or from Address-Event-Representation (AER) temporal contrast vision sensor. Bio-inspired, cortex-like, spikebased features are obtained through event-driven convolution and neural competition. The extracted spike feature patterns are then classified by a network of leaky integrate-and-fire (LIF) spiking neurons, in which the weights are trained using tempotron learning rule. One appealing characteristic of our system is the fully event-driven processing. The input, the features, and the classification are all based on address events (spikes). Experimental results on three datasets have proved the efficacy of the proposed algorithm.