4599693 : Probabilistic learning system

ABSTRACT:   A probabilistic learning system of the type that receives sequential input data and outputs sequences of recognized patterns. The system includes an array of interconnected probabilistic learning elements of the type that receive sequences of objects and outputs sequences of recognized states, the array of learning elements being interconnected to have a number of input learning elements and a number of output learning elements. The input data is partitioned between the input learning elements of the array so that the partitioned input data forms objects provided to the learning elements in an overlapping and redundant manner. The output sequences of recognized states from the output learning elements are collected and combined to provide a sequence of recognized patterns as an output of the probabilistic learning system. The reliability of the learning system is enhanced due to the overlapping and redundant nature in which the input objects are processed through the system and the time required to perform the system task is reduced through the use of parallel processing through the array. Each element of the array provides a signal correspoding to a rating of confidence in the recognized states and this rating of confidence is fed back to the input of the element to cause the element to learn the recognized states when the rating of confidence exceeds a predetermined threshold level. The rating of confidence is also provided to the inputs of prior elements in the array to cause the prior elements to learn their recognized states when the rating of confidence exceeds the predetermined threshold.

U.S. REFERENCES:

28 patents reference this one

Patent No. Inventor Issued Title 3103648 * Hartmanis 9 /1963   3196399 * Kamentsky 7 /1965   3267431 * Greenberg 8 /1966   3414885 * Muller 12 /1968   3440617 * Lesti 4 /1969   3446950 * King, Jr. 5 /1969   3457552 * Asendorf 7 /1969   3562502 Kautz 2 /1971 CELLULAR THRESHOLD ARRAY FOR PROVIDING OUTPUTS REPRESENTING A COMPLEX WEIGHTING FUNCTION OF INPUTS 3566359 Connelly 2 /1971   3576976 Russo 5 /1971 NONLINEAR OPTIMIZING COMPUTER FOR PROCESS CONTROL 3581281 Martin 5 /1971 PATTERN RECOGNITION COMPUTER 3588823 Chow 6 /1971   3601811 Yoshino 8 /1971 LEARNING MACHINE 3613084 Armstrong 10 /1971 TRAINABLE DIGITAL APPARATUS 3623015 Schmitz 11 /1971 STATISTICAL PATTERN RECOGNITION SYSTEM WITH CONTINUAL UPDATE OF ACCEPTANCE ZONE LIMITS 3638196 Nishiyama et al. 1 /1972 LEARNING MACHINE 3646329 Yoshino et al. 2 /1972 ADAPTIVE LOGIC CIRCUIT 3678461 Choate et al. 7 /1972 EXPANDED SEARCH FOR TREE ALLOCATED PROCESSORS 3700866 Taylor 10 /1972 SYNTHESIZED CASCADED PROCESSOR SYSTEM 3701974 Russell 10 /1972 LEARNING CIRCUIT 3702986 Taylor et al. 11 /1972 TRAINABLE ENTROPY SYSTEM 3715730 Smith 2 /1973 MULTI-CRITERIA SEARCH PROCEDURE FOR TRAINABLE PROCESSORS 3716840 Masten et al. 2 /1973 MULTIMODAL SEARCH 3722658 Sarlo 2 /1971 CLOSURE HANDLING AND ORIENTING APPARATUS 3725875 Choate et al. 4 /1973 PROBABILITY SORT IN A STORAGE MINIMIZED OPTIMUM PROCESSOR 3753243 Ricketts, Jr. 8 /1973 PROGRAMMABLE MACHINE CONTROLLER 3934231 Armstrong 1 /1976 Adaptive boolean logic element 3950733 Cooper et al. 4 /1976 Information processing system 3988715 Mullan et al. 10 /1976 Multi-channel recognition discriminator 3999161 van Bilzen et al. 12 /1976 Method and device for the recognition of characters, preferably of figures 4066999 Spanjersberg 1 /1978 Method for recognizing characters 4100370 Suzuki et al. 7 /1978 Voice verification system based on word pronunciation 4189779 Brautingham 2 /1980 Parameter interpolator for speech synthesis circuit 4286330 Isaacson 8 /1981 Autonomic string-manipulation system 4318083 Argyle 3 /1982 Apparatus for pattern recognition 4384273 Ackland et al. 5 /1983 Time warp signal recognition processor for matching signal patterns 4450530 Uinas et al. 5 /1984 Sensorimotor coordinator   * some details unavailable EXEMPLARY CLAIM(s): Show all 23 claims What is claimed is: 19. A probabilistic learning system that receives sequential input data and outputs sequences of recognized patterns, comprising: an array of interconnected probabilistic learning elements that receives sequences of objects and output sequences of recognized states, said array of learning elements being interconnected to have a number of input learning elements and a number of output learning elements the sequences of recognized states from predetermined learning elements being combined to form objects to be received by other learning elements of the array; means for receiving and partitioning the input data between the input learning elements of the array in an overlapping and redundant manner, whereby the partitioned input data become objects provided to the input learning elements; and means for collecting and combining the recognized state sequences from the output learning elements of the array and for providing a sequence of recognized patterns as an output of the probabilistic learning system, whereby the reliability of the learning system is enhanced due to the overlapping and redundant nature in which the input data is processed through the system and the time required to perform the system task is reduced through the use of parallel processing through the array. RELATED U.S. APPLICATIONS: none FOREIGN APPLICATION PRIORITY DATA: none FOREIGN REFERENCES: none OTHER REFERENCES: "Artificial Intelligence", Roberts, Byte 9/81, pp. B-164-178. Jackson, Jr. Introduction to Artificial Intelligence, Petrocelli/Charter New York 1974. "Medicine Intelligence and Communications in Future NASA Missions", IEEE Transactions, Healy, pp. 8-15. "How Artificial is Intelligence", Bennett, Jr. American Scientist, vol. 65, No. 6, Nov.-Dec. 77, pp. 694-702. PRIMARY/ASSISTANT EXAMINERS: Smith; Jerry; Grossman; Jon D. ADDED TO DATABASE: Aug. 22, 1996