Neuromorphic circuit based on the un-supervised learning of biologically inspired spiking neural network for pattern recognition. (November 2022)

• Record Type: Journal Article
• Authors: Nazari, Soheila; Keyanfar, Alireza; Van Hulle, Marc M.
• Is Part Of: Engineering applications of artificial intelligence. Volume 116(2022)
• Publication Date: 2022-11
• Subjects: Spiking pattern recognition network -- PCA -- Bio-inspired learning mechanism -- Neuromorphic circuit -- Hardware implementation; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2022.105430
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: One of the most sophisticated platforms for hosting intelligent systems is bio-inspired. This study proposes pattern recognition hardware using a biologically inspired Spiking Neural Network (SNN) and the new dimensionality reduction approach. The SNN model is based on real neural networks consisting of spiking neurons linked by excitatory and inhibitory synapses activated by excitatory and inhibitory neurotransmitters. Also, a semi-supervised (un-supervised STDP based learning with supervised weight initialization), spike-based learning strategy based on the learning procedure of the nervous system is used to teach the spiking output layer neurons, albeit that the hardware implementation benefits from a semi-supervised approach. The goal of this research is to accurately categorize patterns in the MNIST and CIFAR10 datasets using an SNN-based hardware platform. Due to the limitations of the latter's resources, a dimensionality reduction based on principal component analysis (PCA) is proposed to speed up the processing procedure and reduce the hardware implementation cost. The presented pattern recognition platform is implemented using the Xilinx® VIVADO high-level synthesis platform (HLS). Finally, optimization approaches are used to improve the used space, reduce hardware implementation delay, and speed up the design process. Highlights: An efficient PCA-based pre-processing hardware was developed. A neuromorphic circuit with un-supervised learning was developed for recognition of MNIST and CIFAR10. The bio-inspired training approach and weight initializing can create high recognition accuracy hardware.