Can Turing machine be curious about its Turing test results? Three informal lectures on physics of intelligence

What is the nature of curiosity? Is there any scientific way to understand the origin of this mysterious force that drives the behavior of even the stupidest naturally intelligent systems and is completely absent in their smartest artificial analogs? Can we build AI systems that could be curious about something, systems that would have an intrinsic motivation to learn? Is such a motivation quantifiable? Is it implementable? I will discuss this problem from the standpoint of physics. The relationship between physics and intelligence is a consequence of the fact that correctly predicted information is nothing but an energy resource, and the process of thinking can be viewed as a process of accumulating and spending this resource through the acts of perception and, respectively, decision making. The natural motivation of any autonomous system to keep this accumulation/spending balance as high as possible allows one to treat the problem of describing the dynamics of thinking processes as a resource optimization problem. Here I will propose and discuss a simple theoretical model of such an autonomous system which I call the Autonomous Turing Machine (ATM). The potential attractiveness of ATM lies in the fact that it is the model of a self-propelled AI for which the only available energy resource is the information itself. For ATM, the problem of optimal thinking, learning, and decision-making becomes conceptually simple and mathematically well tractable. This circumstance makes the ATM an ideal playground for studying the dynamics of intelligent behavior and allows one to quantify many seemingly unquantifiable features of genuine intelligence.

[1]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[2]  Huaiyu Zhu.  On Information and Sufficiency , 1997 .

[3]  E. D. Schneider,et al.  Life as a manifestation of the second law of thermodynamics , 1994 .

[4]  J. Hull.  Options, Futures, and Other Derivatives , 1989 .

[5]  Nishio Takayuki,et al.  Deep Learning Tutorial , 2018 .

[6]  Charles H. Bennett,et al.  The thermodynamics of computation—a review , 1982 .

[7]  Waldo Hasperué,et al.  The master algorithm: how the quest for the ultimate learning machine will remake our world , 2015 .

[8]  R. Landauer,et al.  Irreversibility and heat generation in the computing process , 1961, IBM J. Res. Dev..

[9]  J. Hawkins,et al.  On Intelligence , 2004 .

[10]  R. Leighton,et al.  Feynman Lectures on Physics , 1971 .

[11]  William G. Faris.  Shadows of the Mind: A Search for the Missing Science of Consciousness , 1997 .

[12]  Timothy Masters,et al.  Deep Belief Nets in C++ and CUDA C: Volume 3 , 2018, Apress.

[13]  Charles H. Bennett,et al.  Notes on Landauer's Principle, Reversible Computation, and Maxwell's Demon , 2002, physics/0210005.

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

[15]  Dong Yu,et al.  Deep Learning: Methods and Applications , 2014, Found. Trends Signal Process..

[16]  Christoph Adami,et al.  What is information?† , 2016, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[17]  R. Leighton,et al.  The Feynman Lectures on Physics; Vol. I , 1965 .

[18]  Nick Bostrom,et al.  Future progress in artificial intelligence: a poll among experts , 2014, SIGAI.

[19]  M. B. Plenio,et al.  The physics of forgetting: Landauer's erasure principle and information theory , 2001, quant-ph/0103108.

[20]  Roger Penrose,et al.  Shadows of the mind - a search for the missing science of consciousness , 1994 .

[21]  Shane Legg,et al.  A Collection of Definitions of Intelligence , 2007, AGI.

[22]  Ralf Der,et al.  Predictive information and emergent cooperativity in a chain of mobile robots , 2008, ALIFE.

[23]  Christoph Adami,et al.  Annals of the New York Academy of Sciences the Use of Information Theory in Evolutionary Biology , 2022 .

[24]  Francis Heylighen,et al.  Complexity and Self-organization , 2008 .

[25]  Rolf Landauer,et al.  Information is Physical , 1991, Workshop on Physics and Computation.

[26]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[27]  Michael J. Berry,et al.  Predictive information in a sensory population , 2013, Proceedings of the National Academy of Sciences.

[28]  J. Wheeler.  Information, physics, quantum: the search for links , 1999 .

[29]  U. Beyer.  Complexity Entropy And The Physics Of Information , 2016 .

[30]  F. Black,et al.  The Pricing of Options and Corporate Liabilities , 1973, Journal of Political Economy.

[31]  Varol Akman,et al.  Turing Test: 50 Years Later , 2000, Minds and Machines.

[32]  Christoph Endres,et al.  Introduction to Artificial Life , 2000, Künstliche Intell..

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

[34]  B. Jack Copeland,et al.  The Turing Test* , 2000, Minds and Machines.