Where does AlphaGo go: from church-turing thesis to AlphaGo thesis and beyond

An investigation on the impact and significance of the AlphaGo vs. Lee Sedol Go match is conducted, and concludes with a conjecture of the AlphaGo Thesis and its extension in accordance with the Church-Turing Thesis in the history of computing. It is postulated that the architecture and method utilized by the AlphaGo program provide an engineering solution for tackling issues in complexity and intelligence. Specifically, the AlphaGo Thesis implies that any effective procedure for hard decision problems such as NP-hard can be implemented with AlphaGo-like approach. Deep rule-based networks are proposed in attempt to establish an understandable structure for deep neural networks in deep learning. The success of AlphaGo and corresponding thesis ensure the technical soundness of the parallel intelligence approach for intelligent control and management of complex systems and knowledge automation.

[1]  A. Burks,et al.  Theory of Logical Nets , 1953, Proceedings of the IRE.

[2]  Claude E. Shannon,et al.  Computers and Automata , 1953, Proceedings of the IRE.

[3]  Don W. Warren,et al.  Complete Decoding Nets: General Theory and Minimality , 1954 .

[4]  G. Nicholas,et al.  The Phenomenon of Man. , 1955 .

[5]  Arthur W. Burks,et al.  The logic of automata , 1956 .

[6]  Dana S. Scott,et al.  Finite Automata and Their Decision Problems , 1959, IBM J. Res. Dev..

[7]  Albert Lindsey Zobrist,et al.  Feature extraction and representation for pattern recognition and the game of go , 1970 .

[8]  Stephen A. Cook,et al.  The complexity of theorem-proving procedures , 1971, STOC.

[9]  B. Gaines,et al.  THE LOGIC OF AUTOMATA , 1975 .

[10]  Shmuel Winograd,et al.  Complexity Of Computations , 1978, ACM Annual Conference.

[11]  H. Morowitz The phenomenon of man. , 1981, Hospital practice.

[12]  Xin Yao,et al.  Finding Approximate Solutions to NP-Hard Problems by Neural Networks is Hard , 1992, Inf. Process. Lett..

[13]  Ronald L. Rivest,et al.  Training a 3-node neural network is NP-complete , 1988, COLT '88.

[14]  G. Saridis,et al.  Suboptimal control for nonlinear stochastic systems , 1992, [1992] Proceedings of the 31st IEEE Conference on Decision and Control.

[15]  Jean-Yves Potvin,et al.  THE TRAVELING SALESMAN PROBLEM: A NEURAL NETWORK PERSPECTIVE , 1993 .

[16]  John H. Connolly,et al.  CSCW and Artificial Intelligence , 1994, Computer Supported Cooperative Work.

[17]  Fei-Yue Wang,et al.  Implementing Adaptive Fuzzy Logic Controllers with Neural Networks: A Design Paradigm , 1995, J. Intell. Fuzzy Syst..

[18]  M. Budinich Neural networks for NP-complete problems , 1997 .

[19]  I. Osman,et al.  A neural network algorithm for the traveling salesman problem with backhauls , 2003 .

[20]  Wang Feiyue,et al.  Parallel system methods for management and control of complex systems , 2004 .

[21]  Rémi Coulom,et al.  Efficient Selectivity and Backup Operators in Monte-Carlo Tree Search , 2006, Computers and Games.

[22]  A. F. Brown Dark Hero of the Information Age: In Search of Norbert Wiener, the Father of Cybernetics , 2006 .

[23]  Huaguang Zhang,et al.  Adaptive Dynamic Programming: An Introduction , 2009, IEEE Computational Intelligence Magazine.

[24]  Shang-Rong Tsai,et al.  Current Frontiers in Computer Go , 2010, IEEE Transactions on Computational Intelligence and AI in Games.

[25]  Wang Fei-Yue,et al.  Parallel Control: A Method for Data-Driven and Computational Control , 2013 .

[26]  Yuandong Tian,et al.  Better Computer Go Player with Neural Network and Long-term Prediction , 2016, ICLR.

[27]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[28]  John Tromp The Number of Legal Go Positions , 2016, Computers and Games.