Neural network apparatus and method for pattern recognition

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.

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.

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.

A neural network coupled to perform adaptive pattern recognition, said neural network comprising:

• input means for receiving a plurality of input pattern signals I.sub.i and outputting a plurality of corresponding pattern signals X.sub.i (i=1,2,3, . . . , M), wherein each one of said input pattern signals I.sub.i represents a portion of a pattern;
• pattern recognition means for providing a plurality of interim pattern signals V.sub.j (j=1,2,3, . . . , N), wherein each one of said interim pattern signals V.sub.j represents said pattern;
• bottom-up coupling means for coupling said plurality of pattern signals X.sub.i to said pattern recognition means, said bottom-up coupling means having coupling coefficients Z.sub.ij ;
• computation means coupled to said input means for computing a plurality of vigilance parameters P.sub.cj based substantially upon said plurality of pattern signals X.sub.i ;
• top-down coupling means for coupling said pattern signals X.sub.i to said computation means, said top-down coupling means having coupling coefficients Z.sub.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.

A method of performing adaptive pattern recognition using a self-organizing neural network, said neural network comprising a plurality of M input neurons coupled to accept input pattern data signals I.sub.i (i=1,2,3, . . . , M) representing a pattern and a plurality of N output neurons coupled to provide pattern output signals V.sub.j (j=1,2,3, . . . , N) corresponding to said pattern, said neural network further comprising a bottom-up adaptive weight matrix having coefficients Z.sub.ij and coupling said input neurons to said output neurons, and a top-down adaptive weight matrix having coefficients Z.sub.ji and coupling said output neurons to said input neurons, said neural network still further comprising vigilance parameter computing means for computing a plurality of vigilance parameters P.sub.cj based substantially upon said input pattern data signals I.sub.i and said bottom-up adaptive weight matrix coefficients Z.sub.ij, and vigilance parameter comparator means for individually comparing said plurality of computed vigilance parameters P.sub.cj with a predetermined reference vigilance parameter P.sub.r, said method comprising the steps of:

• training said neural network by inputting a plurality of reference pattern data signals I.sub.ir representing a plurality of reference patterns into said plurality of M input neurons;
• analyzing a subject pattern by inputting pattern data signals I.sub.i corresponding thereto into said plurality of M input neurons;
• and
• classifying said subject pattern according to a pattern output signal V.sub.jm from the one of said plurality of N output neurons which corresponds to an associated vigilance parameter P.sub.ajm having the maximum value among a plurality of associated vigilance parameters P.sub.aj, said step of classifying said subject pattern comprising outputting an output pattern signal encoded to represent said subject pattern.