A Functional Architecture Approach to Neural Systemscoward, l andrew (2000) A Functional Architecture Approach to Neural Systems. [Journal (Paginated)] Full text available as:
AbstractThe technology for the design of systems to perform extremely complex combinations of real-time functionality has developed over a long period. This technology is based on the use of a hardware architecture with a physical separation into memory and processing, and a software architecture which divides functionality into a disciplined hierarchy of software components which exchange unambiguous information. This technology experiences difficulty in design of systems to perform parallel processing, and extreme difficulty in design of systems which can heuristically change their own functionality. These limitations derive from the approach to information exchange between functional components. A design approach in which functional components can exchange ambiguous information leads to systems with the recommendation architecture which are less subject to these limitations. Biological brains have been constrained by natural pressures to adopt functional architectures with this different information exchange approach. Neural networks have not made a complete shift to use of ambiguous information, and do not address adequate management of context for ambiguous information exchange between modules. As a result such networks cannot be scaled to complex functionality. Simulations of systems with the recommendation architecture demonstrate the capability to heuristically organize to perform complex functionality.
References in ArticleSelect the SEEK icon to attempt to find the referenced article. If it does not appear to be in cogprints you will be forwarded to the paracite service. Poorly formated references will probably not work. Metadata
Repository Staff Only: item control page |