CAM-Brain

Abstract

A “Darwin Machine” is defined to be a piece of hardware that evolves its own architecture at electronic speeds. A Darwin Machine is an example of “Evolutionary Engineering”, which in turn is defined to be the building of complex structures and dynamics using evolutionary methods. The author believes that evolutionary techniques will dominate 21st century engineering, especially molecular scale (nanotech) engineering, with its gargantuan number of components and complexities. This paper reports on the second year of an ambitious 8 year research project which aims to implement a type of Darwin Machine in the form of a cellular automata based artificial brain with a billion neurons by 2001, which grows/evolves at (nano-)electronic speeds inside a Cellular Automata Machine — ATR’s so-called “CAM-Brain Project”. The basic idea is to use cellular automata based neural networks which grow under evolutionary control at (nano-)electronic speeds. The states of the cellular automata (CA) cells and the CA state transition rules can be stored cheaply in gigabytes of RAM. By using state of the art cellular automata machines, e.g. MIT’s “CAM8” machine ($40,000), which can update 200 million CA cells a second, it may be technically feasible within a year or so to evolve artificial nervous systems containing a thousand neurons, and within 5 years, a million neurons. By the end of the current research project, i.e. 2001, it should be possible using nano-scale electronics to grow/evolve artificial brains containing a billion neurons and upwards. This is our aim.