Identifying Mirror Symmetry Density with Delay in Spiking Neural Networks

TL;DR

This paper introduces a spiking neural network method that rapidly detects symmetry density in spatial data, leveraging coincidence detection and synchronization, with practical implementation in FPGA for applications in vision and robotics.

Contribution

It presents a novel approach using coincidence detection in spiking neurons to identify symmetry density, including a digital FPGA implementation for practical use.

Findings

Effective symmetry detection in spatial data

Fast processing suitable for real-time applications

Successful FPGA implementation demonstrating practicality

Abstract

The ability to rapidly identify symmetry and anti-symmetry is an essential attribute of intelligence. Symmetry perception is a central process in human vision and may be key to human 3D visualization. While previous work in understanding neuron symmetry perception has concentrated on the neuron as an integrator, here we show how the coincidence detecting property of the spiking neuron can be used to reveal symmetry density in spatial data. We develop a method for synchronizing symmetry-identifying spiking artificial neural networks to enable layering and feedback in the network. We show a method for building a network capable of identifying symmetry density between sets of data and present a digital logic implementation demonstrating an 8x8 leaky-integrate-and-fire symmetry detector in a field programmable gate array. Our results show that the efficiencies of spiking neural networks can be harnessed to rapidly identify symmetry in spatial data with applications in image processing, 3D computer vision, and robotics.