Neural network apparatus and method for pattern recognition

Claim 2

An improved self-organizing neural network coupled to perform adaptive pattern recognition in accordance with adaptive resonance theory, said neural network comprising a plurality of input neurons coupled to accept input pattern data representing a pattern, a plurality of output neurons, a bottom-up adaptive weight matrix coupling said input neurons to said output neurons, a top-down adaptive weight matrix coupling said output neurons to said input neurons, and vigilance parameter computing means for computing a plurality of vigilance parameters based substantially upon said input pattern data, said improvement comprising: memory means for storing said plurality of computed vigilance parameters; and pattern classification means for classifying said pattern according to the maximum computed vigilance parameter among said plurality of computed vigilance parameters.

Claim 3

An improved self-organizing neural network coupled to perform adaptive pattern recognition in accordance with adaptive resonance theory, said neural network comprising a plurality of input neurons coupled to accept input pattern data representing a pattern, a plurality of output neurons, a bottom-up adaptive weight matrix coupling said input neurons to said output neurons, a top-down adaptive weight matrix coupling said output neurons to said input neurons, vigilance parameter computing means for computing a plurality of vigilance parameters based substantially upon said input pattern data, and vigilance parameter comparator means for individually comparing said plurality of computed vigilance parameters with a predetermined reference vigilance parameter, said improvement comprising: vigilance parameter adjustment means for selectively adjusting said predetermined reference vigilance parameter in response to said comparisons thereof with said plurality of computed vigilance parameters, said adjustment resulting in a plurality of adjusted reference vigilance parameters; memory means for storing said plurality of adjusted reference vigilance parameters; and pattern classification means for classifying said pattern according to the maximum adjusted reference vigilance parameter among said plurality of adjusted reference vigilance parameters.

Claim 4

An improved self-organizing neural network coupled to perform adaptive pattern recognition in accordance with adaptive resonance theory, said neural network comprising a plurality of input neurons coupled to accept input pattern data representing a pattern, a plurality of output neurons, a bottom-up adaptive weight matrix coupling said input neurons to said output neurons, a top-down adaptive weight matrix coupling said output neurons to said input neurons, vigilance parameter computing means for computing a plurality of vigilance parameters based substantially upon said input pattern data, and vigilance parameter comparator means for individually comparing said plurality of computed vigilance parameters with a predetermined reference vigilance parameter, said improvement comprising: vigilance parameter adjustment means for selectively adjusting said predetermined reference vigilance parameter in response to said comparisons thereof with said plurality of computed vigilance parameters, said adjustment resulting in a plurality of adjusted reference vigilance parameters; memory means for storing said plurality of adjusted reference vigilance parameters; and pattern classification means for classifying said pattern according to the maximum adjusted reference vigilance parameter among said plurality of adjusted reference vigilance parameters.

Claim 5

A neural network coupled to perform adaptive pattern recognition, said neural network comprising: vigilance parameter computing means for computing a plurality of vigilance parameters based substantially upon input pattern data representing a pattern; memory means for storing said plurality of computed vigilance parameters; and pattern classification means for classifying said pattern according to the maximum computed vigilance parameter among said plurality of computed vigilance parameters.

Claim 6

A neural network coupled to perform adaptive pattern recognition, said neural network comprising: vigilance parameter computing means for computing a plurality of vigilance parameters based substantially upon input pattern data representing a pattern; memory means for storing said plurality of computed vigilance parameters; and pattern classification means for classifying said pattern according to the maximum computed vigilance parameter among said plurality of computed vigilance parameters.

Claim 7

A neural network coupled to perform adaptive pattern recognition, said neural network comprising: vigilance parameter adjustment means for selectively adjusting a predetermined reference vigilance parameter in response to comparisons thereof with a plurality of computed vigilance parameters based upon input pattern data representing a pattern, said adjustment resulting in a plurality of adjusted reference vigilance parameters; memory means for storing said plurality of adjusted reference vigilance parameters; and pattern classification means for classifying said pattern according to the maximum adjusted reference vigilance parameter among said plurality of adjusted reference vigilance parameters.

Claim 8

A neural network coupled to perform adaptive pattern recognition, said neural network comprising: vigilance parameter adjustment means for selectively adjusting a predetermined reference vigilance parameter in response to comparisons thereof with a plurality of computed vigilance parameters based upon input pattern data representing a pattern, said adjustment resulting in a plurality of adjusted reference vigilance parameters; memory means for storing said plurality of adjusted reference vigilance parameters; and pattern classification means for classifying said pattern according to the maximum adjusted reference vigilance parameter among said plurality of adjusted reference vigilance parameters.

Claim 9

A neural network coupled to perform adaptive pattern recognition, said neural network comprising: input means for receiving a plurality of input pattern signals I i and outputting a plurality of corresponding pattern signals X i (i=1,2,3, . . . , M), wherein each one of said input pattern signals I i represents a portion of a pattern; pattern recognition means for providing a plurality of interim pattern signals V j (j=1,2,3, . . . , N), wherein each one of said interim pattern signals V j represents said pattern; bottom-up coupling means for coupling said plurality of pattern signals X i to said pattern recognition means, said bottom-up coupling means having coupling coefficients Z ij ; computation means coupled to said input means for computing a plurality of vigilance parameters P cj based substantially upon said plurality of pattern signals X i ; top-down coupling means for coupling said pattern signals X i to said computation means, said top-down coupling means having coupling coefficients Z ji ; a plurality of memory circuits coupled to selectively store said plurality of vigilance parameters; and a pattern classification circuit coupled to generate an output pattern signal representing said pattern based upon said stored plurality of vigilance parameters.

Claim 10

A neural network coupled to perform adaptive pattern recognition, said neural network comprising: input means for receiving a plurality of input pattern signals I i and outputting a plurality of corresponding pattern signals X i (i=1,2,3, . . . , M), wherein each one of said input pattern signals I i represents a portion of a pattern; pattern recognition means for providing a plurality of interim pattern signals V j (j=1,2,3, . . . , N), wherein each one of said interim pattern signals V j represents said pattern; bottom-up coupling means for coupling said plurality of pattern signals X i to said pattern recognition means, said bottom-up coupling means having coupling coefficients Z ij ; computation means coupled to said input means for computing a plurality of vigilance parameters P cj based substantially upon said plurality of pattern signals X i ; top-down coupling means for coupling said pattern signals X i to said computation means, said top-down coupling means having coupling coefficients Z ji ; a plurality of memory circuits coupled to selectively store said plurality of vigilance parameters; and a pattern classification circuit coupled to generate an output pattern signal representing said pattern based upon said stored plurality of vigilance parameters.

Claim 11

A neural network as recited in claim 5 further comprising comparator means for receiving a predetermined reference vigilance parameter P r and for comparing each one of said plurality of computed vigilance parameters P cj therewith, and still further comprising adjustment means for selectively adjusting said reference vigilance parameter P r in response to each one of said comparisons thereof with said plurality of computed vigilance parameters P cj .

Claim 12

A neural network as recited in claim 5, wherein said input means comprises a plurality of M nodes and said input pattern signals I i comprise analog signals.

Claim 13

A neural network as recited in claim 5, wherein said input means comprises a plurality of M digital registers and said input pattern signals I i comprise digital signals.

Claim 14

A neural network as recited in claim 5, wherein said pattern recognition means comprises a plurality of N nodes and said interim pattern signals V j comprise analog signals.

Claim 15

A neural network as recited in claim 5, wherein said pattern recognition means comprises a plurality of N digital registers and said interim pattern signals V j comprise digital signals.

Claim 16

A neural network as recited in claim 5, wherein said bottom-up coupling means comprises a bottom-up adaptive weight matrix having a plurality of transistors coupled to selectively weight said plurality of pattern signals X i , wherein the respective ratios of said weighted pattern signals to corresponding ones of said plurality of pattern signals X i represent said coupling coefficients Z ij .

Claim 17

A neural network as recited in claim 5, wherein said bottom-up coupling means comprises a bottom-up adaptive weight matrix having a plurality of resistors coupled to selectively weight said plurality of pattern signals X i , wherein the respective ratios of said weighted pattern signals to corresponding ones of said plurality of pattern signals X i represent said coupling coefficients Z ij .

Claim 18

A neural network as recited in claim 5, wherein said bottom-up coupling means comprises a bottom-up adaptive weight matrix having a plurality of digital circuits coupled to selectively weight said plurality of pattern signals X i , wherein the respective ratios of said weighted pattern signals to corresponding ones of said plurality of pattern signals X i represent said coupling coefficients Z ij .

Claim 19

A neural network as recited in claim 5, wherein said top-down coupling means comprises a top-down adaptive weight matrix having a plurality of transistors coupled to selectively weight said plurality of pattern signals X i , wherein the respective ratios of said weighted pattern signals to corresponding ones of said plurality of pattern signals X i represent said coupling coefficients Z ji .

Claim 20

A neural network as recited in claim 5, wherein said top-down coupling means comprises a top-down adaptive weight matrix having a plurality of resistors coupled to selectively weight said plurality of pattern signals X i , wherein the respective ratios of said weighted pattern signals to corresponding ones of said plurality of pattern signals X i represent said coupling coefficients Z ji .

Claim 21

A neural network as recited in claim 5, wherein said top-down coupling means comprises a top-down adaptive weight matrix having a plurality of digital circuits coupled to selectively weight said plurality of pattern signals X i , wherein the respective ratios of said weighted pattern signals to corresponding ones of said plurality of pattern signals X i represent said coupling coefficients Z ji .

Claim 22

A neural network as recited in claim 5, wherein said computation means comprises an analog signal summing circuit and said pattern signals X i comprise analog signals, said analog signal summing circuit operating according to the formula: ##EQU10##

Claim 23

A neural network as recited in claim 5, wherein said computation means comprises a digital adder circuit and said pattern signals X i comprise digital signals, said digital adder circuit operating according to the formula: ##EQU11##

Claim 24

A neural network as recited in claim 6, wherein said comparator means comprises an analog comparator circuit, and said computed vigilance parameter P cj and said predetermined reference vigilance parameter P r comprise voltages, said analog comparator circuit being coupled to determine whether said computed vigilance parameter P cj equals or exceeds said predetermined reference vigilance parameter P r and operating according to the formula: ##EQU12##

Claim 25

A neural network as recited in claim 6, wherein said comparator means comprises a digital comparator circuit, and said computed vigilance parameter P cj and said predetermined reference vigilance parameter P r comprise digital signals, said digital comparator circuit being coupled to determine whether said computed vigilance parameter P cj equals or exceeds said predetermined reference vigilance parameter P r and operating according to the formula: ##EQU13##

Claim 26

A neural network as recited in claim 6, wherein said adjustment means comprises an analog signal summing circuit, and said reference vigilance parameter P r and said computed vigilance parameter P cj comprise analog signals.

Claim 27

A neural network as recited in claim 6, wherein said adjustment means comprises a digital adder circuit, and said reference vigilance parameter P r and said computed vigilance parameter P cj comprise digital signals.

Claim 30

A method of performing adaptive pattern recognition using a self-organizing neural network as recited in claim 23, wherein said step of training said neural network comprises the steps of: initializing said coefficients Z ij of said bottom-up adaptive weight matrix, said coefficients Z ji of said top-down adaptive weight matrix, and said value P r of said reference vigilance parameter; applying said reference input pattern data signals I ir representing a reference pattern to said plurality of M input neurons, selectively scaling said reference input pattern data signals I ir by a predetermined scaling factor, and generating corresponding reference pattern signals X ir ; generating within each one of said output neurons a plurality of reference pattern output signals V jr (j=1,2,3, . . . , N) corresponding to said reference pattern; selecting a reference pattern output signal V jrm , said selected reference pattern output signal V jrm corresponding to the one of said output neurons which best represents said reference pattern; computing a vigilance parameter P cjm , said computed vigilance parameter P cjm being associated with said output neuron corresponding to said selected reference pattern output signal V jrm ; comparing said computed vigilance parameter P cjm to said reference vigilance parameter P r ; if P cjm <P r , disabling temporarily said output neuron corresponding to said selected reference pattern output signal V jrm , selecting a new reference pattern output signal V jrm , and repeating the foregoing steps, beginning with said step of computing a vigilance parameter P cjm ; if P cjm ≧P r , adapting the corresponding ones of said coefficients Z ij , Z ji of said bottom-up and top-down adaptive weight matrices; and enabling any output neurons previously disabled in the foregoing disabling step and repeating the foregoing steps, beginning with said step of applying reference input pattern data signals I ir .

Claim 31

A method of performing adaptive pattern recognition using a self-organizing neural network as recited in claim 24, wherein said step of initializing comprises the steps of: selectively initializing said coefficients Z ij of said bottom-up adaptive weight matrix according to the formula: ##EQU14## initializing said coefficients Z ji of said top-down adaptive weight matrix according to the formula: ##EQU15## and selectively initializing said value P r of said reference vigilance parameter according to the formula: < P.sub.r <1.

Claim 32

A method of performing adaptive pattern recognition using a self-organizing neural network as recited in claim 24, wherein said step of generating a plurality of reference pattern output signals V jr is performed according to the formula: ##EQU16##

Claim 33

A method of performing adaptive pattern recognition using a self-organizing neural network as recited in claim 24, wherein said step of selecting a reference pattern output signal V jrm comprises selecting the reference pattern output signal V jrm having the maximum value among all of said reference pattern output signals V jr according to the formula: ##EQU17## by inhibiting all other output neurons not corresponding thereto.

Claim 34

A method of performing adaptive pattern recognition using a self-organizing neural network as recited in claim 24, wherein said step of computing said computed vigilance parameter P cjm is performed according to the formula: ##EQU18##

Claim 35

A method of performing adaptive pattern recognition using a self-organizing neural network as recited in claim 24, wherein said step of adapting said coefficients Z ij , Z ji of said bottom-up and top-down adaptive weight matrices is performed according to the formulas: ##EQU19##

Claim 36

A method of performing adaptive pattern recognition using a self-organizing neural network as recited in claim 23, wherein said step of analyzing a subject pattern comprises the steps of: applying said input pattern data signals I i representing a subject pattern to said plurality of M input neurons, selectively scaling said input pattern data signals I i by a predetermined scaling factor, and generating corresponding pattern signals X i ; computing said plurality of computed vigilance parameters P cj , each one of said plurality of computed vigilance parameters P cj being respectively associated with one of said plurality of N output neurons; and selectively storing said plurality of computed vigilance parameters P cj in a random access memory as said plurality of associated vigilance parameters P aj .

Claim 37

A method of performing adaptive pattern recognition using a self-organizing neural network as recited in claim 30, wherein said step of computing said plurality of computed vigilance parameters P cj is performed according to the formula: ##EQU20##

Claim 38

A method of performing adaptive pattern recognition using a self-organizing neural network as recited in claim 30 further comprising the steps of: re-initializing said value P r of said reference vigilance parameter according to the formula: P.sub.r =1; comparing said plurality of computed vigilance parameters P cj to said reference vigilance parameter P r ; if P cj <P r , reducing said value P r of said reference vigilance parameter by a selectable amount Δ, re-comparing said computed vigilance parameter P cj to said reduced reference vigilance parameter P rrj (where P rrj =P r -Δ), and continuing to reduce said reduced reference vigilance parameter P rrj until P cj ≧P rrj ; if P cj ≧P r , storing said reference vigilance parameter P r in a random access memory as said associated vigilance parameter P aj ; if P cj ≧P rrj , storing said reduced reference vigilance parameter P rrj as said associated vigilance parameter P aj in a random access memory; and repeating the foregoing steps until each one of said plurality of N output neurons has associated respectively therewith an associated vigilance parameter P aj .

Claim 39

A method of performing adaptive pattern recognition using a self-organizing neural network as recited in claim 32, wherein said step of computing said plurality of computed vigilance parameters P cj is performed according to the formula: ##EQU21##