Modeling the Evolution of Retina Neural Network
This work addresses the problem of understanding the evolutionary pathways leading to conserved retinal structures for researchers in computational neuroscience and evolutionary biology, and offers a framework for goal-driven neural network design in machine learning.
This paper explores the evolution of retinal neural networks using a genetic algorithm. The method successfully generates architectures functionally similar to biological retinas, and also discovers effective alternative preprocessing structures and functions.
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.