New Millennium AI and the Convergence of History: Update of 2012

Artificial Intelligence (AI) has recently become a real formal science: the new millennium brought the first mathematically sound, asymptotically optimal, universal problem solvers, providing a new, rigorous foundation for the previously largely heuristic field of General AI and embedded agents. There also has been rapid progress in not quite universal but still rather general and practical artificial recurrent neural networks for learning sequence-processing programs, now yielding state-of-the-art results in real world applications. And the computing power per Euro is still growing by a factor of 100–1,000 per decade, greatly increasing the feasibility of neural networks in general, which have started to yield human-competitive results in challenging pattern recognition competitions. Finally, a recent formal theory of fun and creativity identifies basic principles of curious and creative machines, laying foundations for artificial scientists and artists. Here I will briefly review some of the new results of my lab at IDSIA, and speculate about future developments, pointing out that the time intervals between the most notable events in over 40,000 years or \(2^9\) lifetimes of human history have sped up exponentially, apparently converging to zero within the next few decades. Or is this impression just a by-product of the way humans allocate memory space to past events?

[1]  Jürgen Schmidhuber,et al.  The New AI: General & Sound & Relevant for Physics , 2003, Artificial General Intelligence.

[2]  Ronald J. Williams,et al.  Gradient-based learning algorithms for recurrent networks and their computational complexity , 1995 .

[3]  W. Vent,et al.  Rechenberg, Ingo, Evolutionsstrategie — Optimierung technischer Systeme nach Prinzipien der biologischen Evolution. 170 S. mit 36 Abb. Frommann‐Holzboog‐Verlag. Stuttgart 1973. Broschiert , 1975 .

[4]  Risto Miikkulainen,et al.  Accelerated Neural Evolution through Cooperatively Coevolved Synapses , 2008, J. Mach. Learn. Res..

[5]  Jürgen Schmidhuber,et al.  Ultimate Cognition à la Gödel , 2009, Cognitive Computation.

[6]  Jürgen Schmidhuber,et al.  Formal Theory of Creativity, Fun, and Intrinsic Motivation (1990–2010) , 2010, IEEE Transactions on Autonomous Mental Development.

[7]  N N Schraudolph,et al.  Processing images by semi-linear predictability minimization. , 1997, Network.

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

[9]  Karl Sims,et al.  Evolving virtual creatures , 1994, SIGGRAPH.

[10]  Dr. Marcus Hutter,et al.  Universal artificial intelligence , 2004 .

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

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

[13]  John Langford,et al.  Agnostic active learning , 2006, J. Comput. Syst. Sci..

[14]  Y. LeCun,et al.  Learning methods for generic object recognition with invariance to pose and lighting , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[15]  Luca Maria Gambardella,et al.  Flexible, High Performance Convolutional Neural Networks for Image Classification , 2011, IJCAI.

[16]  Vaclav Smil,et al.  Detonator of the population explosion , 1999, Nature.

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

[18]  Jürgen Schmidhuber,et al.  Gödel Machines: Fully Self-referential Optimal Universal Self-improvers , 2007, Artificial General Intelligence.

[19]  Nuttapong Chentanez,et al.  Intrinsically Motivated Reinforcement Learning , 2004, NIPS.

[20]  Tom Schaul,et al.  Natural Evolution Strategies , 2008, 2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence).

[21]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[22]  Jürgen Schmidhuber,et al.  Unconstrained On-line Handwriting Recognition with Recurrent Neural Networks , 2007, NIPS.

[23]  Harald Haas,et al.  Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication , 2004, Science.

[24]  PAUL J. WERBOS,et al.  Generalization of backpropagation with application to a recurrent gas market model , 1988, Neural Networks.

[25]  Ingo Rechenberg,et al.  Evolutionsstrategie : Optimierung technischer Systeme nach Prinzipien der biologischen Evolution , 1973 .

[26]  Jürgen Schmidhuber,et al.  LSTM recurrent networks learn simple context-free and context-sensitive languages , 2001, IEEE Trans. Neural Networks.

[27]  Jürgen Schmidhuber,et al.  Training Recurrent Networks by Evolino , 2007, Neural Computation.

[28]  Jürgen Schmidhuber,et al.  New Millennium AI and the Convergence of History: Update of 2012 , 2012 .

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

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

[31]  Risto Miikkulainen,et al.  Evolving Neural Networks through Augmenting Topologies , 2002, Evolutionary Computation.

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

[33]  Jürgen Schmidhuber,et al.  Curious model-building control systems , 1991, [Proceedings] 1991 IEEE International Joint Conference on Neural Networks.

[34]  Jürgen Schmidhuber,et al.  Semilinear Predictability Minimization Produces Well-Known Feature Detectors , 1996, Neural Computation.

[35]  Jürgen Schmidhuber,et al.  Offline Handwriting Recognition with Multidimensional Recurrent Neural Networks , 2008, NIPS.

[36]  Jürgen Schmidhuber,et al.  Learning Factorial Codes by Predictability Minimization , 1992, Neural Computation.

[37]  A. Sloman.  Meta-morphogenesis and the Creativity of Evolution , 2012 .

[38]  Jürgen Schmidhuber,et al.  Reinforcement Learning with Self-Modifying Policies , 1998, Learning to Learn.

[39]  Douglas B. Lenat,et al.  Theory Formation by Heuristic Search , 1983, Artificial Intelligence.

[40]  Jürgen Schmidhuber,et al.  Artificial curiosity based on discovering novel algorithmic predictability through coevolution , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[41]  Nikolaus Hansen,et al.  Completely Derandomized Self-Adaptation in Evolution Strategies , 2001, Evolutionary Computation.

[42]  Sven Behnke,et al.  Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition , 2010, ICANN.

[43]  Luca Maria Gambardella,et al.  Deep, Big, Simple Neural Nets for Handwritten Digit Recognition , 2010, Neural Computation.

[44]  Sven Behnke,et al.  Hierarchical Neural Networks for Image Interpretation , 2003, Lecture Notes in Computer Science.

[45]  Jürgen Schmidhuber,et al.  PowerPlay: Training an Increasingly General Problem Solver by Continually Searching for the Simplest Still Unsolvable Problem , 2011, Front. Psychol..

[46]  Jürgen Schmidhuber,et al.  A committee of neural networks for traffic sign classification , 2011, The 2011 International Joint Conference on Neural Networks.

[47]  Luca Maria Gambardella,et al.  Convolutional Neural Network Committees for Handwritten Character Classification , 2011, 2011 International Conference on Document Analysis and Recognition.

[48]  Tom Schaul,et al.  Stochastic search using the natural gradient , 2009, ICML '09.

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

[50]  Eduardo Sontag,et al.  Turing computability with neural nets , 1991 .

[51]  Jürgen Schmidhuber,et al.  Sequence Labelling in Structured Domains with Hierarchical Recurrent Neural Networks , 2007, IJCAI.

[52]  Pierre-Yves Oudeyer,et al.  Intrinsically Motivated Learning of Real-World Sensorimotor Skills with Developmental Constraints , 2013, Intrinsically Motivated Learning in Natural and Artificial Systems.

[53]  Sven Behnke,et al.  Hierarchical Neural Networks for Image Interpretation (Lecture Notes in Computer Science) , 2003 .

[54]  Luca Maria Gambardella,et al.  Better Digit Recognition with a Committee of Simple Neural Nets , 2011, 2011 International Conference on Document Analysis and Recognition.

[55]  Jürgen Schmidhuber,et al.  Evolving neural networks in compressed weight space , 2010, GECCO '10.

[56]  Jürgen Schmidhuber,et al.  Multi-column deep neural networks for image classification , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[57]  Jürgen Schmidhuber,et al.  Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks , 2006, ICML.

[58]  Yi Sun,et al.  Planning to Be Surprised: Optimal Bayesian Exploration in Dynamic Environments , 2011, AGI.

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

[60]  Jürgen Schmidhuber,et al.  On Fast Deep Nets for AGI Vision , 2011, AGI.

[61]  Tom Schaul,et al.  Efficient natural evolution strategies , 2009, GECCO.

[62]  Michael Merritt,et al.  Plenary talk , 2013, PODC '13.

[63]  Jürgen Schmidhuber,et al.  Sequential Constant Size Compressors for Reinforcement Learning , 2011, AGI.

[64]  Alan F. Murray,et al.  Synaptic Rewiring for Topographic Map Formation , 2008, ICANN.

[65]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

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

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

[68]  Andrew G. Barto,et al.  Intrinsic Motivation and Reinforcement Learning , 2013, Intrinsically Motivated Learning in Natural and Artificial Systems.

[69]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[70]  Paul E. Utgoff,et al.  Shift of bias for inductive concept learning , 1984 .

[71]  Geoffrey E. Hinton,et al.  Generating Text with Recurrent Neural Networks , 2011, ICML.

[72]  Benjamin Kuipers,et al.  Bootstrap learning of foundational representations , 2006, Connect. Sci..

[73]  Xin Yao,et al.  A review of evolutionary artificial neural networks , 1993, Int. J. Intell. Syst..

[74]  Jürgen Schmidhuber,et al.  Completely Self-referential Optimal Reinforcement Learners , 2005, ICANN.

[75]  Jürgen Schmidhuber.  2006: Celebrating 75 Years of AI - History and Outlook: The Next 25 Years , 2006, 50 Years of Artificial Intelligence.

[76]  Julian F. Miller,et al.  Genetic and Evolutionary Computation — GECCO 2003 , 2003, Lecture Notes in Computer Science.

[77]  Marco Mirolli,et al.  Intrinsically Motivated Learning in Natural and Artificial Systems , 2013 .

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

[79]  Kunihiko Fukushima,et al.  Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position , 1980, Biological Cybernetics.

[80]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[81]  Raymond C. Kurzweil,et al.  The Singularity Is Near , 2018, The Infinite Desire for Growth.

[82]  Luciano Floridi,et al.  A Look into the Future Impact of ICT on Our Lives , 2006, Inf. Soc..

[83]  Lihong Li,et al.  Learning from Logged Implicit Exploration Data , 2010, NIPS.

[84]  E. Feigenbaum,et al.  Computers and Thought , 1963 .

[85]  Jürgen Schmidhuber,et al.  Philosophers & Futurists, Catch Up! Response to The Singularity , 2012 .

[86]  Jürgen Schmidhuber,et al.  A Fixed Size Storage O(n3) Time Complexity Learning Algorithm for Fully Recurrent Continually Running Networks , 1992, Neural Computation.

[87]  Jürgen Schmidhuber,et al.  Developmental robotics, optimal artificial curiosity, creativity, music, and the fine arts , 2006, Connect. Sci..

[88]  Jürgen Schmidhuber,et al.  A possibility for implementing curiosity and boredom in model-building neural controllers , 1991 .

[89]  Jürgen Schmidhuber,et al.  Learning Precise Timing with LSTM Recurrent Networks , 2003, J. Mach. Learn. Res..

[90]  Jürgen Schmidhuber,et al.  Multi-column deep neural network for traffic sign classification , 2012, Neural Networks.

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

[92]  Risto Miikkulainen,et al.  Efficient Non-linear Control Through Neuroevolution , 2006, ECML.

[93]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[94]  W. J. Studden,et al.  Theory Of Optimal Experiments , 1972 .

[95]  Jürgen Schmidhuber,et al.  Recurrent policy gradients , 2010, Log. J. IGPL.

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

[97]  Yoshua Bengio,et al.  Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies , 2001 .

[98]  Sebastian Thrun,et al.  Learning to Learn , 1998, Springer US.

[99]  Peter Dayan,et al.  Exploration from Generalization Mediated by Multiple Controllers , 2013, Intrinsically Motivated Learning in Natural and Artificial Systems.

[100]  Stephen Hart,et al.  Intrinsically motivated hierarchical manipulation , 2008, 2008 IEEE International Conference on Robotics and Automation.

[101]  Tom Schaul,et al.  Exponential natural evolution strategies , 2010, GECCO '10.