Skip to main content

1993 | OriginalPaper | Buchkapitel

EVOLVABLE HARDWARE Genetic Programming of a Darwin Machine

verfasst von : Hugo de Garis

Erschienen in: Artificial Neural Nets and Genetic Algorithms

Verlag: Springer Vienna

Aktivieren Sie unsere intelligente Suche um passende Fachinhalte oder Patente zu finden.

search-config
loading …

For the past three years, the author has been dreaming of the possibility of building machines which are capable of evolution, called “Darwin Machines”. As a result of several brain storming sessions with some colleagues in electrical engineering, the author now realizes that hardware devices are on the market today, which use “software configurable hardware” technologies that the author believes can be used to build Darwin Machines within a year or two. This paper suggests there are at least two approaches to be taken. The first approach uses “software configurable hardware” chips, e.g. FPGAs (Field Programmable Gate Arrays), HDPLDs (High Density Programmable Logic Devices), or possibly a new generation of chips based on the ideas that FPGAs etc embody. The second approach uses a special hardware device called a “hardware accelerator” which accelerates the simulation in software of digital hardware devices containing up to several hundred thousand gates. Darwin Machines will be essential if artificial nervous systems are to be evolved for biots (i.e. biological robots) which consist of thousands of evolved neural network modules (called GenNets). The evolution time of 1000-GenNet biots will need to be reduced by many orders of magnitude if they are to be built at all. It is for this reason that Darwin Machines may prove to be a breakthrough in biotic design. When molecular scale technologies come on line in the late 1990s, the Darwin Machine approach will probably be the only way to build self assembling, self testing molecular scale devices.

Metadaten
Titel
EVOLVABLE HARDWARE Genetic Programming of a Darwin Machine
verfasst von
Hugo de Garis
Copyright-Jahr
1993
Verlag
Springer Vienna
DOI
https://doi.org/10.1007/978-3-7091-7533-0_64

Neuer Inhalt