Pictorial reasoning with cell assemblies

Abstract

A bstract. We introduce a biologically and psychologically plausible neuronal model which could explain how pictorial reasoning is carried out by the human brain. This biologically inspired model throws some light on how some problem-solving abilities might actually be performed by the human brain using neural cell assemblies. It also highlights the bene ts of distributed representation. These bene ts include the ability to learn from experience, heuristics resulting from picture representation and the ability to deal with noisy information. The description of the reasoning process by formation of associations gives exibility and power in operation. The proper way to use it, the proper data representations and the proper network architecture are presented in this paper.

The Quantum Binding Problem in the Context of Associative Memory

“…According to [ 11 , 12 , 14 , 27 ] the identity of an object can be represented by a binary pattern which is normalized for size and orientation. Its location in the x -axis is represented by a binary vector of the size of the abscissa of the pictogram representing the object.…”

Sub-Symbols and Icons

“…Image representation also enables learning from examples through the definition of similarity between different problems. Empirical experiments in popular problem-solving domains of Artificial Intelligence, like robot in a maze, block world or eight-puzzle indicated that the distance between the states in the problem space is actually related to the distance between the icons representing the states [45,47,48]. It was also shown by computer experiments that learning from examples speeds up the search in the problem space considerably [46].…”

“…This problem is called the permutation problem, and a neural associative memory architecture, in which the problem could be simplified, was presented by Wichert et al [45,47,48]. We do not need to form all possible permutations.…”

“…In this case, the association can be executed, and the conclusion sub-vectors of the association can replace the corresponding sub-vectors. Out of several possible associations, one has to be chosen [45,47,48].…”

Proto logic and neural subsymbolic reasoning

“…The similarity between the corresponding vectors can indicate the distance between the sub-symbols representing the state. Empirical experiments in popular problemsolving domains of Artificial Intelligence, like a robot in a maze, block world or 8puzzle indicate that the distance between the states in the problem space is actually related to the similarity between the images representing the states Wichert [2001Wichert [ , 2009, Wichert et al [2008].…”