Application of Hopfield Network to Saccades

TL;DR

This paper proposes a Hopfield neural network model to emulate human eye saccades, demonstrating its potential for shift-invariant pattern recognition through computer simulations.

Contribution

It introduces a novel Hopfield network architecture that integrates location and identification tasks for saccade emulation.

Findings

Network performs location and identification tasks cooperatively

Simulation results support applicability to shift-invariant pattern recognition

Model mimics human eye movement mechanisms

Abstract

Human eye movement mechanisms (saccades) are very useful for scene analysis, including object representation and pattern recognition. In this letter, a Hopfield neural network to emulate saccades is proposed. The network uses an energy function that includes location and identification tasks. Computer simulation shows that the network performs those tasks cooperatively. The result suggests that the network is applicable to shift-invariant pattern recognition.