Simulation of an array-based neural net model
暂无分享,去创建一个
Research in cognitive science suggests that much of cognition involves the rapid manipulation of complex data structures. However, it is very unclear how this could be realized in neural networks or connectionist systems. A core question is: how could the interconnectivity of items in an abstract-level data structure be neurally encoded? The answer appeals mainly to positional relationships between activity patterns within neural arrays, rather than directly to neural connections in the traditional way. The new method was initially devised to account for abstract symbolic data structures, but it also supports cognitively useful spatial analogue, image-like representations. As the neural model is based on massive, uniform, parallel computations over 2D arrays, the massively parallel processor is a convenient tool for simulation work, although there are complications in using the machine to the fullest advantage. An MPP Pascal simulation program for a small pilot version of the model is running.
[1] Geoffrey E. Hinton,et al. Symbols Among the Neurons: Details of a Connectionist Inference Architecture , 1985, IJCAI.
[2] V. Mountcastle,et al. An organizing principle for cerebral function : the unit module and the distributed system , 1978 .
[3] P. A. Kolers. Perception and representation. , 1983, Annual review of psychology.
[4] P. Johnson-Laird. Mental models , 1989 .
[5] J. Richardson. Mental imagery and human memory , 1980 .