Data processing: generic control systems or specific application – Specific application – apparatus or process – Robot control
Patent
1997-03-10
2000-02-22
Hafiz, Tariq R.
Data processing: generic control systems or specific application
Specific application, apparatus or process
Robot control
700250, 706 16, 706 26, G06E 100, G06F 1545
Patent
active
060290994
ABSTRACT:
A self-learning network with: (a) one or more sensor(s) in one or more sensor unit(s) with a plurality of memory cells that forward-select values of one or more intermediate variable(s) I.sub.1, J.sub.1, . . . according to their stored values and the conditions identified by its sensor(s) in a given sensing and action period, (b) with or without one or more intermediate units with a plurality of bidirectional memory cells that forward-select a value of one or more intermediate output variable(s) I.sub.2, J.sub.2, . . . according to their stored values and the value(s) of the intermediate input variable(s) I.sub.1, J.sub.1, . . . , and (c) one or more actuator(s) in one or more actuator unit(s) connected to one or more intermediate variable(s) I.sub.1, J.sub.1, . . . or I.sub.2, J.sub.2, . . . with a plurality of bidirectional memory cells that forward-select values of one or more actuators according to their stored values and the value(s) of its intermediate variable(s) I.sub.1, J.sub.1, . . . or I.sub.2, J.sub.2, . . . . The bidirectional memory cells then back-select a value of each intermediate co-variable I.sub.1 ', J.sub.1 ', . . . or I.sub.2 ', J.sub.2 ', . . . according to their stored values and the actions that actually occur within each specific sensing and action periods. The stored values are reduced in the forward-selecting memory cells, and the stored values are increased in the back-selecting bidirectional memory cells, and are increased in the memory cells at the intersection of the back-selected value(s) of the intermediate co-variable I.sub.1 ', J.sub.1 ', . . . and the conditions identified by its sensor(s) in that sensing and action period.
REFERENCES:
patent: 4258425 (1981-03-01), Ramsey et al.
patent: 4366551 (1982-12-01), Holtz
patent: 4802103 (1989-01-01), Faggin et al.
patent: 5075868 (1991-12-01), Andes et al.
patent: 5161203 (1992-11-01), Buckley
patent: 5226092 (1993-07-01), Chen
patent: 5687076 (1997-11-01), Pam
patent: 5710870 (1998-01-01), Ohm et al.
patent: 5719480 (1998-02-01), Bock et al.
patent: 5724489 (1998-03-01), Yamamoto
patent: 5781697 (1998-07-01), Jeong
patent: 5781705 (1998-07-01), Endo
patent: 5870527 (1999-02-01), Fujikawa et al.
patent: 5872893 (1999-02-01), Takenaka et al.
Hafiz Tariq R.
Pender Michael
LandOfFree
Method of a network that learns does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method of a network that learns, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method of a network that learns will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-528483