Neuron unit

A neuron unit for processing a plurality of input signals and for outputting an output signal which is indicative of a result of the processing, the neuron unit comprising:

• a) input line means for receiving the input signals;
• b) forward process means, coupled to said input line means, and including:
• supplying means for supplying weight functions, and
• operation means for carrying out an operation on each of the input signals using one of the weight functions and for outputting the output signal;
• and
• c) self-learning means, coupled to said forward process means, and including:
• function generating means for generating new weight functions based on errors between the output signal of said forward process means and teaching signals;
• and
• varying means for varying the weight functions supplied by the supplying means of the forward process means to the new weight functions generated by said generating means,
• said supplying means including:
• first memory means for storing each weight function in the form of a binary value, and
• first generating means, coupled to said first memory means, for generating a random pulse train based on each binary value stored in said first memory means,
• said random pulse train describing each weight function in the form of a pulse signal having a pulse density which is defined by at least one of a number of first values and a number of second values of the pulse signal within a predetermined time, where the first and second values are arranged at random and the first and second values respectively correspond to high and low binary signal levels.