https://www.ncbi.nlm.nih.gov/pubmed/29735249
An adaptive deep Q-learning strategy for handwritten digit recognition.
Author information
- 1
- Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China; Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing 100124, China. Electronic address: junfeiq@bjut.edu.cn.
- 2
- Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China; Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing 100124, China. Electronic address: xiaowangqsd@163.com.
- 3
- Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China; Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing 100124, China. Electronic address: wenjing.li@bjut.edu.cn.
- 4
- Department of Obstetrics Gynecology, Civil Aviation General Hospital, Beijing 100123, China. Electronic address: cmcajh@163.com.
Abstract
Handwritten digits recognition is a challenging problem in recent years. Although many deep learning-based classification algorithms are studied for handwritten digits recognition, the recognition accuracy and running time still need to be further improved. In this paper, an adaptive deep Q-learning strategy is proposed to improve accuracy and shorten running time for handwritten digit recognition. The adaptive deep Q-learning strategy combines the feature-extracting capability of deep learning and the decision-making of reinforcement learning to form an adaptive Q-learning deep belief network (Q-ADBN). First, Q-ADBN extracts the features of original images using an adaptive deep auto-encoder (ADAE), and the extracted features are considered as the current states of Q-learning algorithm. Second, Q-ADBN receives Q-function (reward signal) during recognition of the current states, and the final handwritten digits recognition is implemented by maximizing the Q-function using Q-learning algorithm. Finally, experimental results from the well-known MNIST dataset show that the proposed Q-ADBN has a superiority to other similar methods in terms of accuracy and running time.
KEYWORDS:
Adaptive Q-learning deep belief network; Adaptive deep auto-encoder; Deep learning; Handwritten digits recognition; Reinforcement learning
- PMID:
- 29735249
- DOI:
- 10.1016/j.neunet.2018.02.010
adaptive Q-learning deep belief network (Q-ADBN)
201805 Neural Netw An adaptive deep Q-learning strategy for handwritten digit recognition.pdf