ADAPTIVE PROCESSOR ARRAY CAPABLE OF LEARNING VARIABLE ASSOCIATIONS USEFUL IN RECOGNIZING CLASSES OF INPUTS

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.