Enhancing efficiency of object recognition in different categorization levels by reinforcement learning in modular spiking neural networks

TL;DR

This paper introduces a biologically inspired hierarchical spiking neural network model with reinforcement learning that improves object recognition accuracy across different categorization levels without external classifiers.

Contribution

It presents a novel modular spiking neural network framework with reinforcement learning for multi-level object recognition, mimicking biological visual processing.

Findings

Achieved significant accuracy improvements on three benchmark datasets.

Demonstrated effective recognition at superordinate, basic, and subordinate levels.

Utilized earliest spike information for classification without external classifiers.

Abstract

The human visual system contains a hierarchical sequence of modules that take part in visual perception at superordinate, basic, and subordinate categorization levels. During the last decades, various computational models have been proposed to mimic the hierarchical feed-forward processing of visual cortex, but many critical characteristics of the visual system, such actual neural processing and learning mechanisms, are ignored. Pursuing the line of biological inspiration, we propose a computational model for object recognition in different categorization levels, in which a spiking neural network equipped with the reinforcement learning rule is used as a module at each categorization level. Each module solves the object recognition problem at each categorization level, solely based on the earliest spike of class-specific neurons at its last layer, without using any external classifier. According to the required information at each categorization level, the relevant band-pass filtered images are utilized. The performance of our proposed model is evaluated by various appraisal criteria with three benchmark datasets and significant improvement in recognition accuracy of our proposed model is achieved in all experiments.