Abstract | ||
---|---|---|
This paper argues that it will soon become technologically possible to build artificial brains at relatively low cost. The proposed approach to doing this is to evolve large numbers (tens of thousands) of neural network modules, each with its own simple function, and then interconnect them inside a computer that would execute the neural signaling of the whole brain in real time, performing functions such as controlling the behaviors of a robot. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1109/AHS.2006.50 | AHS |
Keywords | Field | DocType |
whole brain,artificial brains,neural network module,artificial brain,low cost,large number,evolving building block modules,real time,own simple function,hardware accelerators,neural network,moore law,high level languages,field programmable gate arrays,high level language,artificial neural networks,field programmable gate array,neural net,hardware,evolutionary algorithm,fpga,hardware accelerator,chip,computer networks,automatic control,evolutionary computation | Evolutionary algorithm,Computer science,Artificial brain,Field-programmable gate array,Evolutionary computation,High-level programming language,Hardware acceleration,Artificial neural network,Computer hardware,Control reconfiguration,Embedded system | Conference |
Volume | Issue | ISSN |
2006 | null | null |
ISBN | Citations | PageRank |
0-7695-2614-4 | 0 | 0.34 |
References | Authors | |
1 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hugo de Garis | 1 | 460 | 103.58 |
de Garis, H. | 2 | 12 | 4.33 |