A Handwritten Digit Recognition Method Based on Deep Q-Learning Strategy

Abstract

A handwritten digit recognition method based on a deep Q-learning strategy belongs to the field of artificial intelligence and pattern recognition, aiming at the problem of low recognition accuracy of the handwritten digit standard object MNIST database. First, the deep auto-encoder (DAE) is used to extract the abstract features of the original signal, and the Q learning algorithm takes the encoding feature of the original signal by DAE as the current state. Then, a reward value is obtained by classifying and identifying the current state, and the reward value is returned to the Q learning algorithm for iterative update. High-accuracy recognition of handwritten digits is accomplished by maximizing the reward value. The present invention combines deep learning with perception ability and reinforcement learning with decision-making ability, and forms Q deep belief network (Q-DBN) by combining deep self-encoder and Q learning algorithm, which improves recognition accuracy and shortens the time Identify 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 handwritten digits, the present invention combines deep reinforcement learning theory to propose a handwritten digit recognition method based on deep Q-learning strategy

Images