Handwritten numeral recognition method based on deep Q learning strategy

Abstract

The invention provides a handwritten numeral recognition method based on a deep Q learning strategy, belongs to the field of artificial intelligence and pattern recognition and solves the problem of low identification precision of a handwritten numeral standard object MNIST database. The method is characterized by, to begin with, carrying out abstract feature extraction on an original signal through a deep auto-encoder (DAE), Q learning algorithm using coding characteristics of the DAE for the original signal as a current state; then, carrying out classification and identification on the current state to obtain a reward value, and returning the reward value to the Q learning algorithm to carry out iterative update; and maximizing the reward value to finish high-precision identification of handwritten numerals. The method combines deep learning having perception capability and reinforcement learning having decision-making ability and forms a Q deep belief network (Q-DBN) through combination of the deep auto-encoder and the Q learning algorithm, thereby improving identification precision, and meanwhile, reducing identification time.

Description

technical field [0001] The invention belongs to the field of artificial intelligence and pattern recognition, relates to a handwritten digit recognition method based on a deep Q learning strategy, and is an innovative application technology combining deep learning and reinforcement learning. Background technique [0002] In recent years, with the continuous development of artificial intelligence technology and pattern recognition technology, handwritten digit recognition has been widely used in postal mail sorting, medical data processing, and other computer vision fields. Handwritten digit recognition is a challenging task due to the large number of different handwritten points and handwriting categories. At this stage, many pattern recognition methods have been applied to handwritten digit recognition, such as classification methods based on deep learning models, artificial neural network methods, and support vector machine classifiers. Among these existing recognition me...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the problem that the existing pattern recognition methods are difficult to meet the increasingly higher requirements for the recognition accuracy of h

Images