Modeling the Evolution of Retina Neural Network

TL;DR

This paper uses a genetic algorithm to model the evolution of retinal neural networks, discovering architectures similar to biological retinas and alternative structures, with implications for understanding evolution and improving neural network design.

Contribution

It introduces a genetic algorithm framework to simulate retinal evolution, generating both biologically similar and alternative neural architectures.

Findings

Generated architectures resemble biological retina structures

Discovered alternative neural network designs with different functions

Framework can guide goal-driven neural network development

Abstract

Vital to primary visual processing, retinal circuitry shows many similar structures across a very broad array of species, both vertebrate and non-vertebrate, especially functional components such as lateral inhibition. This surprisingly conservative pattern raises a question of how evolution leads to it, and whether there is any alternative that can also prompt helpful preprocessing. Here we design a method using genetic algorithm that, with many degrees of freedom, leads to architectures whose functions are similar to biological retina, as well as effective alternatives that are different in structures and functions. We compare this model to natural evolution and discuss how our framework can come into goal-driven search and sustainable enhancement of neural network models in machine learning.