Neural network circuit device

A neural network circuit device that calculates a degree of similarity between an input of a learning phase and an input of an inference phase using a perceptron obtained by modeling a nerve cell, the neural network circuit device comprising:

• a second adder circuit that adds for each component of a vector of the inference phase;
• a minimum value selection circuit that selects a minimum value for each component of a vector of the learning phase and the vector of the inference phase;
• a third adder circuit that adds for each component of a Fuzzy AND vector obtained by a Fuzzy AND operation using the Fuzzy AND operation of extracting a minimum value component for each component of the vector in the minimum value selection circuit;
• a fourth adder circuit that adds a component of an input vector at a time of the learning phase;
• a fifth adder circuit that adds outputs of the second adder circuit and the fourth adder circuit;
• a doubler circuit that doubles an output of the third adder circuit;
• and
• a divider circuit that divides an output value of the doubler circuit by an output value of the fifth adder circuit.