Probabilistic learning element

Details Probabilistic learning element Probabilistic learning element

1984-01-16

1986-10-28

Smith, Jerry

Boots, shoes, and leggings

364200, 364900, 364134, G09C 0000, G06F 100, G05B 1508

Patent

active

046202862

ABSTRACT:
A probabilistic learning element for performing task independent sequential pattern recognition. The element receives sequences of objects and outputs sequences of recognized states composed of objects. A plurality of memory elements are utilized to store received objects in sequence and for storing in context learned information including previously learned states, objects contained in previously learned states, positional information for each object in a learned state and other predetermined types of knowledge relating to previously learned states and objects contained therein. The element correlates sequences of received objects with learned information relating to previously learned states for providing conditional probabilities to possible sequences of recognized states. The most likely state sequence is determined and outputted as a recognized sequence when the element detects that a state has ended. The memory for storing learned information is a context organized memory including a plurality of tree structures having various types of information stored in nodes thereof with certain of the tree structures including at each node an attribute list referring to other tree structures whereby searching is facilitated and unnecessary searching eliminated. The element derives support coefficients relating to how much information was available when calculating conditional probabilities and support coefficients and conditional probabilities are combined to provide a rating of confidence. When the rating of confidence exceeds a predetermined level, the element is caused to store the outputted recognized state sequence as a learned state sequence with the memories storing various types of knowledge relating to the learned sequence of states.

REFERENCES:
patent: 3103648 (1963-09-01), Hartmanis
patent: 3196399 (1965-07-01), Kamentsley et al.
patent: 3267431 (1966-08-01), Greenberg et al.
patent: 3414885 (1968-12-01), Muller
patent: 3440617 (1969-04-01), Lesti
patent: 3446950 (1969-05-01), King, Jr. et al.
patent: 3457552 (1969-07-01), Asendorf
patent: 3562502 (1971-02-01), Kautz
patent: 3566359 (1971-02-01), Connelly
patent: 3576976 (1971-05-01), Russo
patent: 3581281 (1971-05-01), Martin
patent: 3588823 (1971-06-01), Chow et al.
patent: 3601811 (1971-08-01), Yoshino
patent: 3613084 (1971-10-01), Armstrong
patent: 3623015 (1971-11-01), Schmitz et al.
patent: 3638196 (1972-01-01), Nishiyama et al.
patent: 3646329 (1972-02-01), Yoshino et al.
patent: 3678461 (1972-07-01), Choate et al.
patent: 3700866 (1972-10-01), Taylor
patent: 3701974 (1972-10-01), Russell
patent: 3702986 (1972-11-01), Taylor et al.
patent: 3715730 (1973-02-01), Smith et al.
patent: 3716840 (1973-02-01), Masten et al.
patent: 3725875 (1973-04-01), Choate et al.
patent: 3753243 (1973-08-01), Ricketts, Jr.
patent: 3772658 (1973-11-01), Sarlo
patent: 3934231 (1976-01-01), Armstrong
patent: 3950733 (1976-04-01), Cooper et al.
patent: 3988715 (1976-10-01), Mullan et al.
patent: 3999161 (1976-12-01), van Bilizem et al.
patent: 4066999 (1978-01-01), Spanjersberg
patent: 4189779 (1980-02-01), Brautingham
patent: 4286330 (1981-08-01), Isaacson
patent: 4318083 (1982-03-01), Argule
patent: 4384273 (1983-05-01), Ackland et al.
patent: 4450530 (1984-05-01), Uinas
patent: 4504970 (1985-03-01), Werth et al.
patent: 4507760 (1985-03-01), Fraser
Artificial Intelligence, Roberts BYTE, pp. 164-178, Sep. 1981.
Introduction to Artificial Intelligence, Jackson, pp. 368-380, Petrocelli Charter, New York, 1974.
"Machine Intelligence and Communications in Future NASA Missions", Healy, IEEE Communications, pp. 8-15, Nov. 1981.
"How Artificial is Intelligence?", Bennet, Jr.; American Scientist, pp. 694-702, vol. 65, No. 6, Nov.-Dec. 1977.

Affiliated with

Also associated with

Rating

Probabilistic learning element does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Probabilistic learning element, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Probabilistic learning element will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1350579