Breaking the Synaptic Dogma: Evolving a Neuro-inspired Developmental Network

Abstract

Abstract. The majority of articial neural networks are static and lifeless and do not change themselves within a learning environment. In these models learning is seen as the process of obtaining the strengths of connections between neurons (i.e. weights). We refer to this as the 'synaptic dogma'. This is in marked contrast with biological networks which have time dependent morphology and in which practically all neural aspects can change or be shaped by mutual interactions and interactions with an external environment. Inspired by this and many aspects of neuroscience, we have designed a new kind of neural network. In this model, neurons are represented by seven evolved programs that model particular components and aspects of biological neurons (dendrites, soma, axons, synapses, electrical and developmental behaviour). Each network begins as a small randomly generated network of neurons. When the seven programs are run, the neurons, dendrites, axons and synapses can increase or decrease in number and change in interaction with an external environment. Our aim is to show that it is possible to evolve programs that allow a network to learn through experience (i.e. encode the ability to learn). We report on our continuing investigations in the context of learning how to play checkers.

Evolution, development and learning using self-modifying cartesian genetic programming

“…However, natural evolution does not work in this way, instead evolution operates at the very much lower level of genetic code and learning in organisms is an emergent consequence of many underlying processes and interactions with an external environment. The essential point here is that all learning occurs in the lifetime of the organism, a fact recently emphasized in [4,5]. From the point of view of this paper, the key point is that evolution has invented learning algorithms (inasmuch as physical learning processes can be simulated by algorithms).…”