Brain and Mind 4 (2):169-188 (2003)
This article discusses the properties of a controllable, flexible, hybrid parallel computing architecture that potentially merges pattern recognition and arithmetic. Humans perform integer arithmetic in a fundamentally different way than logic-based computers. Even though the human approach to arithmetic is both slow and inaccurate it can have substantial advantages when useful approximations ( intuition ) are more valuable than high precision. Such a computational strategy may be particularly useful when computers based on nanocomponents become feasible because it offers a way to make use of the potential power of these massively parallel systems. Because the system architecture is inspired by neuroscience and is applied to cognitive problems, occasional mention is made of experimental data from both fields when appropriate.
|Keywords||arithmetic attractor cognitive science computation data representation network of networks neural network|
|Categories||categorize this paper)|
References found in this work BETA
No references found.
Citations of this work BETA
No citations found.
Similar books and articles
Parallel Architectures and Mental Computation.Andrew Wells - 1993 - British Journal for the Philosophy of Science 44 (3):531-542.
Deciding Arithmetic Using SAD Computers.Mark Hogarth - 2004 - British Journal for the Philosophy of Science 55 (4):681-691.
Models of Arithmetic and Upper Bounds for Arithmetic Sets.Alistair H. Lachlan & Robert I. Soare - 1994 - Journal of Symbolic Logic 59 (3):977-983.
The Strength of Nonstandard Methods in Arithmetic.C. Ward Henson, Matt Kaufmann & H. Jerome Keisler - 1984 - Journal of Symbolic Logic 49 (4):1039-1058.
Added to index2009-01-28
Total downloads59 ( #86,322 of 2,152,538 )
Recent downloads (6 months)3 ( #225,917 of 2,152,538 )
How can I increase my downloads?