The New AI: General & Sound & Relevant for Physics

Most traditional artificial intelligence (AI) systems of the past 50 years are either very limited, or based on heuristics, or both. The new millennium, however, has brought substantial progress in the field of theoretically optimal and practically feasible algorithms for prediction, search, inductive inference based on Occam's razor, problem solving, decision making, and reinforcement learning in environments of a very general type. Since inductive inference is at the heart of all inductive sciences, some of the results are relevant not only for AI and computer science but also for physics, provoking nontraditional predictions based on Zuse's thesis of the computer-generated universe.

[1]  Jürgen Schmidhuber,et al.  Reinforcement Learning in Markovian and Non-Markovian Environments , 1990, NIPS.

[2]  C. Schmidhuber Strings from Logic , 2000, hep-th/0011065.

[3]  Corso Elvezia Discovering Solutions with Low Kolmogorov Complexity and High Generalization Capability , 1995 .

[4]  Ray J. Solomonoff,et al.  The Application of Algorithmic Probability to Problems in Artificial Intelligence , 1985, UAI.

[5]  P. Werbos,et al.  Beyond Regression : "New Tools for Prediction and Analysis in the Behavioral Sciences , 1974 .

[6]  Marcus Hutter The Fastest and Shortest Algorithm for all Well-Defined Problems , 2002, Int. J. Found. Comput. Sci..

[7]  Ofi rNw8x'pyzm,et al.  The Speed Prior: A New Simplicity Measure Yielding Near-Optimal Computable Predictions , 2002 .

[8]  Marcus Hutter,et al.  Algorithmic Information Theory , 1977, IBM J. Res. Dev..

[9]  A. Whitaker The Fabric of Reality , 2001 .

[10]  Allen Newell,et al.  GPS, a program that simulates human thought , 1995 .

[11]  Jürgen Schmidhuber,et al.  Sequential Decision Making Based on Direct Search , 2001, Sequence Learning.

[12]  Marcus Hutter,et al.  Self-Optimizing and Pareto-Optimal Policies in General Environments based on Bayes-Mixtures , 2002, COLT.

[13]  Stephen Wolfram,et al.  Universality and complexity in cellular automata , 1983 .

[14]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[15]  SolomonoffR. Complexity-based induction systems , 2006 .

[16]  Jürgen Schmidhuber,et al.  Shifting Inductive Bias with Success-Story Algorithm, Adaptive Levin Search, and Incremental Self-Improvement , 1997, Machine Learning.

[17]  John von Neumann,et al.  Theory Of Self Reproducing Automata , 1967 .

[18]  K. Gödel Über formal unentscheidbare Sätze der Principia Mathematica und verwandter Systeme I , 1931 .

[19]  Gary James Jason,et al.  The Logic of Scientific Discovery , 1988 .

[20]  Jürgen Schmidhuber,et al.  Solving POMDPs with Levin Search and EIRA , 1996, ICML.

[21]  H. Everett "Relative State" Formulation of Quantum Mechanics , 1957 .

[22]  David P. DiVincenzo,et al.  Quantum information and computation , 2000, Nature.

[23]  Gregory J. Chaitin,et al.  A recent technical report , 1974, SIGA.

[24]  G. Hooft Quantum gravity as a dissipative deterministic system , 1999, gr-qc/9903084.

[25]  Hilary Putnam,et al.  Trial and error predicates and the solution to a problem of Mostowski , 1965, Journal of Symbolic Logic.

[26]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[27]  Ray J. Solomonoff,et al.  A Formal Theory of Inductive Inference. Part I , 1964, Inf. Control..

[28]  Sepp Hochreiter,et al.  Learning to Learn Using Gradient Descent , 2001, ICANN.

[29]  Andrew W. Moore,et al.  Reinforcement Learning: A Survey , 1996, J. Artif. Intell. Res..

[30]  Schmidhuber Juergen,et al.  The New AI: General & Sound & Relevant for Physics , 2003 .

[31]  Michael I. Jordan,et al.  Forward Models: Supervised Learning with a Distal Teacher , 1992, Cogn. Sci..

[32]  A. Kolmogorov Three approaches to the quantitative definition of information , 1968 .

[33]  E. Mark Gold,et al.  Limiting recursion , 1965, Journal of Symbolic Logic.

[34]  H. Cantor Ueber eine Eigenschaft des Inbegriffs aller reellen algebraischen Zahlen. , 1984 .

[35]  M. Mahoney,et al.  History of Mathematics , 1924, Nature.

[36]  Marcus Hutter,et al.  Towards a Universal Theory of Artificial Intelligence Based on Algorithmic Probability and Sequential Decisions , 2000, ECML.

[37]  J. Bell On the Problem of Hidden Variables in Quantum Mechanics , 1966 .

[38]  Shirley Dex,et al.  JR 旅客販売総合システム(マルス)における運用及び管理について , 1991 .

[39]  Jürgen Schmidhuber,et al.  Optimal Ordered Problem Solver , 2002, Machine Learning.

[40]  Jürgen Schmidhuber,et al.  Algorithmic Theories of Everything , 2000, ArXiv.

[41]  Thomas G. Dietterich What is machine learning? , 2020, Archives of Disease in Childhood.

[42]  Gregory J. Chaitin,et al.  On the Length of Programs for Computing Finite Binary Sequences: statistical considerations , 1969, JACM.

[43]  田中 正,et al.  SUPERSTRING THEORY , 1989, The Lancet.

[44]  Jürgen Schmidhuber,et al.  The Speed Prior: A New Simplicity Measure Yielding Near-Optimal Computable Predictions , 2002, COLT.

[45]  Péter Gács,et al.  On the relation between descriptional complexity and algorithmic probability , 1981, 22nd Annual Symposium on Foundations of Computer Science (sfcs 1981).

[46]  J. Rissanen Stochastic Complexity and Modeling , 1986 .

[47]  B. Widrow,et al.  The truck backer-upper: an example of self-learning in neural networks , 1989, International 1989 Joint Conference on Neural Networks.

[48]  Jean-Pierre Bourguignon,et al.  Mathematische Annalen , 1893 .

[49]  Neri Merhav,et al.  Universal Prediction , 1998, IEEE Trans. Inf. Theory.

[50]  T. Toffoli,et al.  Conservative logic , 2002, Collision-Based Computing.

[51]  Jürgen Schmidhuber,et al.  Discovering Neural Nets with Low Kolmogorov Complexity and High Generalization Capability , 1997, Neural Networks.

[52]  H. Stowell The emperor's new mind R. Penrose, Oxford University Press, New York (1989) 466 pp. $24.95 , 1990, Neuroscience.

[53]  Michael Barr,et al.  The Emperor's New Mind , 1989 .

[54]  Jürgen Schmidhuber,et al.  A Computer Scientist's View of Life, the Universe, and Everything , 1999, Foundations of Computer Science: Potential - Theory - Cognition.

[55]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[56]  A. Church Review: A. M. Turing, On Computable Numbers, with an Application to the Entscheidungsproblem , 1937 .

[57]  L. E. J. Brouwer,et al.  Over de Grondslagen der Wiskunde , 2009 .

[58]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[59]  Leopold Löwenheim Über Möglichkeiten im Relativkalkül , 1915 .

[60]  Jürgen Schmidhuber,et al.  Goedel Machines: Self-Referential Universal Problem Solvers Making Provably Optimal Self-Improvements , 2003, ArXiv.

[61]  Jürgen Schmidhuber,et al.  Bias-Optimal Incremental Problem Solving , 2002, NIPS.

[62]  Ming Li,et al.  An Introduction to Kolmogorov Complexity and Its Applications , 2019, Texts in Computer Science.

[63]  T. Erber,et al.  Randomness in quantum mechanics—nature's ultimate cryptogram? , 1985, Nature.

[64]  Marcus Hutter General Loss Bounds for Universal Sequence Prediction , 2001, ICML.

[65]  D. C. Cooper,et al.  Theory of Recursive Functions and Effective Computability , 1969 .

[66]  Charles H. Moore,et al.  Forth - a language for interactive computing , 1970 .

[67]  J. Urgen Schmidhuber A Computer Scientist's View of Life, the Universe, and Everything , 1997 .

[68]  Marcus Hutter A Gentle Introduction to The Universal Algorithmic Agent AIXI , 2003 .

[69]  Vladimir Vapnik,et al.  The Nature of Statistical Learning , 1995 .

[70]  R. Solomonoff A SYSTEM FOR INCREMENTAL LEARNING BASED ON ALGORITHMIC PROBABILITY , 1989 .

[71]  A. Turing On computable numbers, with an application to the Entscheidungsproblem , 1937, Proc. London Math. Soc..

[72]  Jürgen Schmidhuber,et al.  Hierarchies of Generalized Kolmogorov Complexities and Nonenumerable Universal Measures Computable in the Limit , 2002, Int. J. Found. Comput. Sci..

[73]  Konrad Zuse,et al.  Rechnender Raum , 1991, Physik und Informatik.