| M.A. Arbib, Artificial intelligence and brain theory: Unities and diversities, Ann. Biomed. Eng., 3, 238-274, 1975. |
....not all parallel computers are equally suitable for a particular problem [3] In that light artificial neural networks are, depending on their specific characteristic, rather easily viable on parallel hardware of all sorts. This comes from the inherent parallelism of their biological original [4] [9] The many implementations support this very impressively [10] 16] These days there are three main reasons to implement neural networks on specialised hardware. While some parallel implementations are intended to adapt a technical model as close as possible to its biological original, the ....
M.A. Arbib, Artificial intelligence and brain theory: Unities and diversities, Ann. Biomed. Eng., 3, 238-274, 1975.
.... the application of diverse knowledge to the same aspects of the problem and from the application of the same knowledge to diverse aspects of the Similar uses of the aggregation of partial solutions arise in systems using the locus model [51] relaxation [50, 63] and the cooperating experts [2, 27, 36] paradigms. FUNCTIONALLY ACCURATE, COOPERATIVE DISTRIBUTED SYSTEMS 9 problem. If sufficient constraints are available during this search process, incorrect partial solutions will naturally die out because it will not be possible to piece them together into more encompassing partial solutions. ....
Michael A. Arbib. Artificial intelligence and brain theory: Unities and diversities. Annals of Biomedical Engineering, 3:238--274,
.... appeals to theorists who think that serial machines are too weak and must be replaced by radically new parallel machines (Fahlman and Hinton, 1986) while on the biological side it appeals to those who believe that cognition can only be understood if we study it as neuroscience (e.g. Arbib, 1975; Sejnowski, 1981) It is also attractive to psychologists who think that much of the mind (including the part involved in using imagery) is not discrete (e.g. Kosslyn Hatfield, 1984) or who think that cognitive science has not paid enough attention to stochastic mechanisms or to holistic ....
Arbib, M. (1975). Artificial intelligence and brain theory: Unities and diversities. Biomedical Engineering,3 238-274.
....the effectiveness, robustness, and psychological validity of this approach. Implications for schema theory and for building robust vision systems are also discussed. 2 Schema Theory Schema theory has been used by many scientists to account for human perceptual and cognitive functions (Arbib 1975, 1987, 1989; Bartlett 1932; Head and Holmes 1911; Hochberg 1978,Piaget 1952, 1971; Rumelhart 1975, 1980;Rumelhart and Ortony 1977; Schmidt 1975) A schema is a package that contains stereotypical knowledge about an object or a process. Schemas serve as building blocks for cognitive functions, ....
Arbib, M. A. (1975). Artificial intelligence and brain theory: Unities and diversities. Annals of Biomedical Engineering, 3:238--274.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC