ELM-based convolutional neural networks making move prediction in Go
With the rapid development of machine learning, artificial intelligence (AI) has drawn much more attention. Under this circumstances, abstract strategy games, such as chess, checkers and Go, have been a fascinating problem of AI research. Most of the existing state-of-the-art Go programs used deep neural network technology, like convolutional neural networks (CNNs). However, CNNs require multiple iterations to optimize weights and spend a lot of training time. Therefore, in this paper, in order to solve the above shortcomings, we propose a new learning algorithm ECNN, which integrates CNNs with extreme learning machine (ELM). We remove pooling layers of CNNs and insert ELM layers between convolutional layers. The newly added ELM layers will be updated in back-propagation process, and they accelerate the convergence of weights in CNNs. Therefore, our ECNN can reduce the training time of CNNs. Further, we propose ECNN-Go algorithm, which applies ECNN to Go game. Because of the advantage of ECNN, ECNN-Go algorithm has the fast learning speed to make move prediction in Go game. Finally, the experimental results show the efficiency and accuracy of ECNN algorithm and demonstrate the strength of ECNN-Go.
KeywordsArtificial intelligence Go programs Convolutional neural networks Extreme learning machine
This research is partially supported by National Natural Science Foundation of China under Grant Nos. 61672145, 61572121, 61602323, 61702086 and U1401256, and the China Postdoctoral Science Foundation under Grant No. 2016M591455.
Compliance with ethical standards
Conflict of interest
The authors declare that they have no potential conflict of interest.
Human participants and animals
This article does not contain any studies involving human participants and/or animals by any of the authors.
Informed consent was obtained from all individual participants.
- Cheng Y, Yuan Y, Chen L, Giraud-Carrier CG, Wang G (2017) Complex event-participant planning and its incremental variant. In: 33rd IEEE international conference on data engineering, ICDE 2017, San Diego, CA, USA, April 19–22, 2017, pp 859–870Google Scholar
- Collobert R, Weston J (2008) A unified architecture for natural language processing: deep neural networks with multitask learning. In: International conference, pp 160–167Google Scholar
- Cui D, Huang GB, Liu T (2016) Smile detection using pair-wise distance vector and extreme learning machine. In: International joint conference on neural networks, pp 2298–2305Google Scholar
- Enzenberger M (1996) The integration of a priori knowledge into a go playing neural network. http://www.markus-enzenbergerde/neurogohtml
- Guo L, Ding S (2015) A hybrid deep learning CNN-ELM model and its application in handwritten numeral recognition. J Comput Inf Syst 11(7):2673–2680Google Scholar
- He K, Sun J (2015) Convolutional neural networks at constrained time cost. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5353–5360Google Scholar
- Huang GB, Zhu QY, Siew CK (2005) Extreme learning machine: a new learning scheme of feedforward neural networks. In: IEEE international joint conference on neural networks, 2004. Proceedings, vol 2, pp 985–990Google Scholar
- Oord A, Den RV, Dieleman S, Schrauwen B (2013) Deep content-based music recommendation. In: International conference on neural information processing systems, pp 2643–2651Google Scholar
- Rafique MA, Pedrycz W, Jeon M (2017) Vehicle license plate detection using region-based convolutional neural networks. Soft Comput. https://doi.org/10.1007/s00500-017-2696-2
- Springenberg JT, Dosovitskiy A, Brox T, Riedmiller M (2014) Striving for simplicity: the all convolutional net. arXiv preprint arXiv:1412.6806
- Stern D, Herbrich R, Graepel T (2006) Bayesian pattern ranking for move prediction in the game of go. In: International conference, pp 873–880Google Scholar
- Sutskever I, Nair V (2008) Mimicking go experts with convolutional neural networks. Artif Neural Netw ICANN 2008:101–110Google Scholar
- Tian Y, Zhu Y (2015) Better computer go player with neural network and long-term prediction. Comput Sci. arXiv preprint arXiv:1511.06410v3
- Wang XZ, Zhang T, Wang R (2017) Noniterative deep learning: incorporating restricted Boltzmann machine into multilayer random weight neural networks. IEEE Trans Syst Man Cybern Syst PP(99):1–10Google Scholar
- Wang Z, Wang X (2017) A deep stochastic weight assignment network and its application to chess playing. J Parallel Distrib Comput. https://doi.org/10.1016/j.jpdc.2017.08.013
- Yen SJ, Yang TN, Chen C, Hsu SC (2007) Pattern matching in go game records. In: International conference on innovative computing, information and control, pp 297–297Google Scholar
- Zhu R, Wang B, Yang X, Zheng B, Wang G (2017) SAP: improving continuous top-k queries over streaming data. IEEE Trans Knowl Data Eng PP(99):1–1Google Scholar