Adaptive processor array capable of learning variable associatio

Details Adaptive processor array capable of learning variable associatio Adaptive processor array capable of learning variable associatio

1985-03-15

1989-05-30

Shaw, Gareth D.

Boots, shoes, and leggings

3642322, 3642319, G06F 700, G06F 1518

Patent

active

048356808

ABSTRACT:
An adaptive processor array is capable of learning certain flexible or variable associations which learned associations are useful in recognizing classes of inputs, i.e., capable of associating certain types of inputs to fall in the same output basin or field. The adaptive processor array comprises a plurality of identical processing cells arranged in parallel columns and rows to form a two dimensional matrix. Each of the cells in the array include logic and a memory for storing an internal state. The first row of cells in the array form a parallel input to the array and the last row of cells in the array form a parallel output from the array. The cells in the intermediate rows of the array between the first and last row of the array, except for end cells, are individually coupled to two cells in a previous cell row that are positioned diagonally relative to each such row cell and are also individually coupled to two cells in a subsequent row of the array that are positioned diagonally relative to each such row cell. Logic in each cell computes a new output based upon the two inputs received from the diagonal cells in the previous row, which output, based upon whether cell is programmed to follow a rule of attraction or a rule of dissociation, is utilized to move the internal integer value of the cell toward one of two stages, one state being a state of dissimilarity and the other state being a state of similarity. The state of dissimilarity is also referred to as a state of dissociation, separation or expansion.

REFERENCES:
patent: 3106698 (1986-05-01), Unger
patent: 3273125 (1966-09-01), Jakowatz
patent: 3496387 (1970-02-01), Hendrix
patent: 3566359 (1971-02-01), Connelly
patent: 3678461 (1972-07-01), Choate et al.
patent: 4060713 (1972-09-01), Golay
patent: 4065808 (1985-01-01), Schomberg et al.
patent: 4193115 (1980-03-01), Albas
patent: 4215401 (1985-08-01), Holsztynski et al.
patent: 4254474 (1981-03-01), Cooper et al.
patent: 4270169 (1981-03-01), Hunt et al.
patent: 4384273 (1971-02-01), Ackland et al.
patent: 4395699 (1980-03-01), Sternberg
patent: 4493048 (1985-01-01), Kung et al.
patent: 4533993 (1985-08-01), McCanny et al.
patent: 4591980 (1986-05-01), Huberman et al.
patent: 4599692 (1986-07-01), Tan et al.
patent: 4599693 (1986-07-01), Denenberg
D. H. Lawrie, "Access and Alignment of Data in an Array Processor," IEEE Transactions on Computers, pp. 1145-1155, Dec. 1975.
Beurle, "Properties of a Mass of Cells Capable of Regenerating Pulses" Royal Society of London Philosophical Trans., vol. 240 (B.667) pp. 8 et seq. (1956).
D. R. Smith et al., "Maintained Activity in Neural Nets", ACM 1969.
G. M. Edelman et al., "Selective Networks Capable of Representative Transformations . . . Memory" Proceedings of National Academy of Science, vol. 79, pp. 2091-2095 (Mar., 1982).
W. H. Kautz, "Cellular Logic-In-Memory Arrays", IEEE Transactions on Computers, pp. 1566-1569, Dec. 1971.
D. d'Humieres & Huberman, "Dynamics of Self-Organization in Complex Adaptive Networks", J. Statistical Physics, vol. 34 (314), pp. 361-379, Feb. 1984.
Huberman et al., "Adaptation and Self-Repair in Parallel Computing Structures", Physical Review Letters, vol. 52(12), pp. 1048-1051, Mar. 19, 1984.
Huberman, "Dynamics of Computing Structures", Physica Scripta, vol. T9, pp. 165-169, 1985.
Muller, "Adwendungen lernfahiger Automaten", Regelungstechnik, vol. 13(9), pp. 410-417, Sep., 1965-English Translation of p. 411, right-hand col., last paragraph to p. 412, full left-hand col. included.
Huberman et al., "Dynamic Associations in Nonlinear Computing Arrays", Physica Scripta, vol. 32, pp. 271-273, Oct. 1985.
Hogg et al., "Parallel Computing Structures Capable of Flexible Associations and Recognition of Fuzzy Inputs", Journal of Statistical Physics, vol. 41(1/2), pp. 115-123, Oct. 1985.

Affiliated with

Also associated with

Rating

Adaptive processor array capable of learning variable associatio does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Adaptive processor array capable of learning variable associatio, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Adaptive processor array capable of learning variable associatio will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2158273