CONSTRUCTION METHOD FOR ARTIFICIAL INTELLIGENCE ULTRA DEEP LAYER LEARNING MODEL, ARTIFICIAL INTELLIGENCE ULTRA DEEP LAYER LEARNING DEVICE, GENERAL PURPOSE MOBILE TERMINAL DEVICE ON WHICH ARTIFICIAL INTELLIGENCE ULTRA DEEP LAYER LEARNING MODEL IS MOUNTED, AND PROGRAM OF ARTIFICIAL INTELLIGENCE ULTRA DEEP LAYER LEARNING MODEL

摘要

PROBLEM TO BE SOLVED: To present a new artificial intelligence model whose calculation complexity is lower and efficiency is higher than a conventional deep layer learning model.SOLUTION: A plurality of information to be input by an object function is input into each node of an input layer by involving into no-teacher machine learning, and mutually connected with the no-teacher machine learning among each node of the input layer and a hidden layer. The hidden layer calculates an output reference value based on a learning value obtained by the no-teacher machine learning, a threshold value of a trigger of a cerebral nerve, or a sampling learning value. An output layer determines an excitation level by the output reference value of all the hidden layers.SELECTED DRAWING: None