Method of learning binary system

A process for performing binary learning using a binary learning network including:

• an input layer having binary input terminals;
• a coupling layer;
• a first binary gate layer with first similar logical elements;
• a second binary gate layer with second similar logical elements;
• and
• an output layer;
• wherein each coupling condition between adjacent layers is limited to a one way direction from an inlet side to an outlet side, and each layer has independent routes without mutual coupling conditions;
• having means for limiting selection of a coupling condition to either one of a direct coupling condition or a coupling condition routed through an inverter in the coupling layer, relative to routes from respective signal units in the input layer to respective signal units in the first binary gate layer, such that the selected coupling condition is adapted to eliminate or decrease the respective errors between original output signals at the output layer and monitor signals in the learning network;
• the process comprising the acts of:
• (1) selecting one of the coupling conditions in the case of the original output signal being different from the monitor signal, and neglecting the learning.in the case wherein both signals are the same;
• (2) learning by selecting one of the coupling conditions between the signal units in the input layer and the signal units in the first binary gate layer in order of a unit selection from a highest position to a lowest position in the first binary gate layer, and to select all input terminals in each unit at the same time or the highest position to the lowest position in the input layer;
• and
• (3) after selecting the coupling condition to the lowest positioned unit, again performing the learning onto the highest position as is necessary.