Brain-Like Approximate Reasoning
نویسنده
چکیده
Humans can easily recognize objects as complex as faces even if they have not seen them in such conditions before. We would like to find out computational basis of this ability. As an example of our approach we use the neurophysiological data from the visual system. In the retina and thalamus simple light spots are classified, in V1 oriented lines and in V4 simple shapes. The feedforward (FF) pathways by extracting above attributes from the object form hypotheses. The feedback (FB) pathways play different roles – they form predictions. In each area structure related predictions are tested against hypotheses. We formulate a theory in which different visual stimuli are described through their condition attributes. Responses in LGN, V1, and V4 neurons to different stimuli are divided into several ranges and are treated as decision attributes. Applying rough set theory (Pawlak, 1991 –[1]) we have divided our stimuli into equivalent classes in different brain areas. We propose that relationships between decision rules in each area are determined in two ways: by different logic of FF and FB pathways: FF pathways gather a huge number of possible objects attributes together using logical “AND” (drivers), and FB pathways choose the right one mainly by logical “OR” (modulators).
منابع مشابه
PROPERTY ANALYSIS OF TRIPLE IMPLICATION METHOD FOR APPROXIMATE REASONING ON ATANASSOVS INTUITIONISTIC FUZZY SETS
Firstly, two kinds of natural distances between intuitionistic fuzzy sets are generated by the classical natural distance between fuzzy sets under a unified framework of residual intuitionistic implication operators. Secondly, the continuity and approximation property of a method for solving intuitionistic fuzzy reasoning are defined. It is proved that the triple implication method for intuitio...
متن کاملWhat Is Approximate Reasoning?
Approximate reasoning for the Semantic Web is based on the idea of sacrificing soundness or completeness for a significant speedup of reasoning. This is to be done in such a way that the number of introduced mistakes is at least outweighed by the obtained speed-up. When pursuing such approximate reasoning approaches, however, it is important to be critical not only about appropriate application...
متن کاملOn Foundations and Applications of the Paradigm of Granular Rough Computing
Granular computing, initiated by Lotfi A. Zadeh, has acquired wide popularity as a tool for approximate reasoning, fusion of knowledge, cognitive computing. The need for formal methods of granulation, and means for computing with granules, has been addressed in this work by applying methods of rough mereology. Rough mereology is an extension of mereology taking as the primitive notion the notio...
متن کاملQuick Comparison of the Efficiency of Fuzzy Operatios Used in FLC
The practical realization of the Fuzzy Logic Controler (FLC) usually depends on the application. Using the parameter-depended group of fuzzy operators like distance based operators in the approximate reasoning process the FLC components can be adapted to achieve better results. The program language environment, applied by simulation, supports the choosing of suitable fuzzy operators and their p...
متن کاملApproximate Reasoning about Complex Objects in Distributed Systems: Rough Mereological Formalization ?
We propose an approach to approximate reasoning by systems of intelligent agents based on the paradigm of rough mereology. In this approach, the knowledge of each agent is formalized as an information system (a data table) from which similarity measures on objects manipulated by this agent are inferred. These similarity measures are based on rough mereological inclusions which formally render d...
متن کاملA Correspondence Framework between Three-Valued Logics and Similarity-Based Approximate Reasoning
This paper focuses on approximate reasoning based on the use of similarity spaces. Similarity spaces and the approximated relations induced by them are a generalization of the rough set-based approximations of Pawlak [17, 18]. Similarity spaces are used to define neighborhoods around individuals and these in turn are used to define approximate sets and relations. In any of the approaches, one w...
متن کامل