论文信息 - A teachable pattern describing and recognizing program

A teachable pattern describing and recognizing program

Abstract The paper discusses an adaptive pattern recognition program that learns to recognize coded line drawings, and to describe the structure of the pattern by giving the hierarchical organization of its subparts, and the spatial relationships between them. Emphasis is on mechanisms that allow learning (directed by feedback from a human trainer), and on the methods of abstracting, storing, and retrieving chunks of graphic information for use in subsequent pattern recognition and description. Some similarities to the perceptual process in humans are noted.

Leonard Uhr | R. W. Sauvain | L. Uhr

[1] H. Barlow. Summation and inhibition in the frog's retina , 1953, The Journal of physiology.

[2] H. Sherman,et al. A quasi-topological method for the recognition of line patterns , 1959, IFIP Congress.

[3] D H HUBEL,et al. THE VISUAL CORTEX OF THE BRAIN. , 1963, Scientific American.

[4] R. Narasimhan,et al. Syntax-directed interpretation of classes of pictures , 1966, CACM.

[5] Marvin Minsky,et al. Steps toward Artificial Intelligence , 1995, Proceedings of the IRE.

[6] L Uhr,et al. Pattern-string learning programs. , 1964, Behavioral science.

[7] H. Kazmierczak,et al. The potential field as an aid to character recognition , 1959, IFIP Congress.

[8] Dave L. Londe,et al. Computers in the study of learning: namer—A pattern-recognition system for generating sentences about relations between line drawings , 1964, ACM '65.