Results 1  10
of
18
Formal Theory of Creativity, Fun, and Intrinsic Motivation (19902010)
"... The simple but general formal theory of fun & intrinsic motivation & creativity (1990) is based on the concept of maximizing intrinsic reward for the active creation or discovery of novel, surprising patterns allowing for improved prediction or data compression. It generalizes the traditio ..."
Abstract

Cited by 75 (15 self)
 Add to MetaCart
The simple but general formal theory of fun & intrinsic motivation & creativity (1990) is based on the concept of maximizing intrinsic reward for the active creation or discovery of novel, surprising patterns allowing for improved prediction or data compression. It generalizes the traditional field of active learning, and is related to old but less formal ideas in aesthetics theory and developmental psychology. It has been argued that the theory explains many essential aspects of intelligence including autonomous development, science, art, music, humor. This overview first describes theoretically optimal (but not necessarily practical) ways of implementing the basic computational principles on exploratory, intrinsically motivated agents or robots, encouraging them to provoke event sequences exhibiting previously unknown but learnable algorithmic regularities. Emphasis is put on the importance of limited computational resources for online prediction and compression. Discrete and continuous time formulations are given. Previous practical but nonoptimal implementations (1991, 1995, 19972002) are reviewed, as well as several recent variants by others (2005). A simplified typology addresses current confusion concerning the precise nature of intrinsic motivation.
Gödel machines: Fully selfreferential optimal universal selfimprovers
 Goertzel and C. Pennachin, Artificial General Intelligence
, 2006
"... Summary. We present the first class of mathematically rigorous, general, fully selfreferential, selfimproving, optimally efficient problem solvers. Inspired by Kurt Gödel’s celebrated selfreferential formulas (1931), such a problem solver rewrites any part of its own code as soon as it has found ..."
Abstract

Cited by 27 (13 self)
 Add to MetaCart
(Show Context)
Summary. We present the first class of mathematically rigorous, general, fully selfreferential, selfimproving, optimally efficient problem solvers. Inspired by Kurt Gödel’s celebrated selfreferential formulas (1931), such a problem solver rewrites any part of its own code as soon as it has found a proof that the rewrite is useful, where the problemdependent utility function and the hardware and the entire initial code are described by axioms encoded in an initial proof searcher which is also part of the initial code. The searcher systematically and efficiently tests computable proof techniques (programs whose outputs are proofs) until it finds a provably useful, computable selfrewrite. We show that such a selfrewrite is globally optimal—no local maxima!—since the code first had to prove that it is not useful to continue the proof search for alternative selfrewrites. Unlike previous nonselfreferential methods based on hardwired proof searchers, ours not only boasts an optimal order of complexity but can optimally reduce any slowdowns hidden by the O()notation, provided the utility of such speedups is provable at all. 1
Gödel Machines: SelfReferential Universal Problem Solvers Making Provably Optimal SelfImprovements
, 2003
"... An old dream of computer scientists is to build an optimally efficient universal problem solver. We show how to solve arbitrary computational problems in an optimal fashion inspired by Kurt Gödel's celebrated selfreferential formulas (1931). Our Gödel machine's initial software includes ..."
Abstract

Cited by 19 (8 self)
 Add to MetaCart
(Show Context)
An old dream of computer scientists is to build an optimally efficient universal problem solver. We show how to solve arbitrary computational problems in an optimal fashion inspired by Kurt Gödel's celebrated selfreferential formulas (1931). Our Gödel machine's initial software includes an axiomatic description of: the Gödel machine's hardware, the problemspecific utility function (such as the expected future reward of a robot), known aspects of the environment, costs of actions and computations, and the initial software itself (this is possible without introducing circularity). It also includes a typically suboptimal initial problemsolving policy and an asymptotically optimal proof searcher searching the space of computable proof techniques  that is, programs whose outputs are proofs. Unlike previous approaches, the selfreferential Gödel machine will rewrite any part of its software, including axioms and proof searcher, as soon as it has found a proof that this will improve its future performance, given its typically limited computational resources. We show that selfrewrites are globally optimal  no local minima!since provably none of all the alternative rewrites and proofs (those that could be found by continuing the proof search) are worth waiting for.
New millennium AI and the convergence of history
 Challenges to Computational Intelligence
, 2007
"... 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. At ..."
Abstract

Cited by 8 (4 self)
 Add to MetaCart
(Show Context)
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. At the same time there has been rapid progress in practical methods for learning true sequenceprocessing programs, as opposed to traditional methods limited to stationary pattern association. Here we will briefly review some of the new results, 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 byproduct of the way humans allocate memory space to past events? 1
Algorithmic Information Theory [ a brief nontechnical guide to the field]
, 2007
"... This article is a brief guide to the field of algorithmic information theory (AIT), its underlying philosophy, and the most important concepts. AIT arises by mixing information theory and computation theory to obtain an objective and absolute notion of information in an individual object, and in so ..."
Abstract

Cited by 4 (4 self)
 Add to MetaCart
(Show Context)
This article is a brief guide to the field of algorithmic information theory (AIT), its underlying philosophy, and the most important concepts. AIT arises by mixing information theory and computation theory to obtain an objective and absolute notion of information in an individual object, and in so doing gives rise to an objective and robust notion of randomness of individual objects. This is in contrast to classical information theory that is based on random variables and communication, and has no bearing on information and randomness of individual objects. After a brief overview, the major subfields,
Mixing cognitive science concepts with computer science algorithms and data structures: An integrative approach to strong AI
 In AAAI Spring Symposium Series
, 2006
"... We posit that, given the current state of development of cognitive science, the greatest synergies between this field and artificial intelligence arise when one adopts a high level of abstraction. On the one hand, we suggest, cognitive science embodies some interesting, potentially general principle ..."
Abstract

Cited by 2 (1 self)
 Add to MetaCart
We posit that, given the current state of development of cognitive science, the greatest synergies between this field and artificial intelligence arise when one adopts a high level of abstraction. On the one hand, we suggest, cognitive science embodies some interesting, potentially general principles regarding cognition under limited resources, and AI systems that violate these principles should be treated with skepticism. But on the other hand, attempts to precisely emulate human cognition in silicon are hampered by both their ineffectiveness at exploiting the power of digital computers, and the current paucity of algorithmlevel knowledge as to how human cognition takes place. We advocate a focus on artificial general intelligence design. This
Theories of artificial intelligence – Metatheoretical considerations
 Theoretical Foundations of Artificial General Intelligence
, 2012
"... This chapter addresses several central metatheoretical issues of AI and AGI. After analyzing the nature of the field, three criteria for desired theories are proposed: correctness, concreteness, and compactness. The criteria are clarified in the AI context, and using them, the current situation in ..."
Abstract

Cited by 2 (2 self)
 Add to MetaCart
This chapter addresses several central metatheoretical issues of AI and AGI. After analyzing the nature of the field, three criteria for desired theories are proposed: correctness, concreteness, and compactness. The criteria are clarified in the AI context, and using them, the current situation in the field is evaluated. 1.1. The problem of AI theory Though it is a common practice for a field of science or engineering to be guided and identified by the corresponding theories, the field of Artificial Intelligence (AI) seems to be an exception. After more than half of a century since its formation, AI still has no widely accepted theory, and in the related discussions the following opinions are often heard: • “The best model of intelligence is the human brain itself (and all theories are merely poor approximations...)” • “There is no need for any new theory, since AI can be built according to X (depending on who said it, the X can be mathematical logic, probability theory, theory of computation,...)” • “A theory of AI has to be established piece by piece, and we are starting from Y (depending on who said it, the Y can be search, reasoning, learning, perception, actions,...)” • “There cannot be any good theory of intelligence (since intelligence is so complicated, though our work is obviously central to it...) ” • “Theoretical debating is a waste of time (and we should focus on practical applications. For example, an intelligent system should be able to...)” • “A good theory only comes at the end of the research (so don’t worry about it now, and it will come as long as we continue the current research on...)” There is a historical reason for this situation. Though the idea of “thinking machine” can be traced further back in history, the field of AI was started from the realization that computers, though initially designed to do numerical calculations, can be made to carry out other mental activities, such as theorem proving and game playing, which are hard 1
The Evaluation of AGI Systems
"... The paper surveys the evaluation approaches used in AGI research, and argues that the proper way of evaluation is to combine empirical comparison with human intelligence and theoretical analysis of the assumptions and implications of the AGI models. Approaches of Evaluation In recent years, the prob ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
The paper surveys the evaluation approaches used in AGI research, and argues that the proper way of evaluation is to combine empirical comparison with human intelligence and theoretical analysis of the assumptions and implications of the AGI models. Approaches of Evaluation In recent years, the problem of evaluation is getting more and more attention in the field of Artificial General Intelligence, or AGI (GB09; LIIL09; LGW09; MAP + 09; Was09). Though the evaluation of research results is important in any field of scientific research, the problem has special difficulty in the current context of AGI, since the research activities belong to many different paradigms, and there seems to be no “neutral”
Extending Universal Intelligence Models with Formal Notion of Representation
"... Abstract. Solomonoff induction is known to be universal, but incomputable. Its approximations, namely, the Minimum Description (or Message) Length (MDL) principles, are adopted in practice in the efficient, but nonuniversal form. Recent attempts to bridge this gap leaded to development of the Repre ..."
Abstract
 Add to MetaCart
(Show Context)
Abstract. Solomonoff induction is known to be universal, but incomputable. Its approximations, namely, the Minimum Description (or Message) Length (MDL) principles, are adopted in practice in the efficient, but nonuniversal form. Recent attempts to bridge this gap leaded to development of the Representational MDL principle that originates from formal decomposition of the task of induction. In this paper, possible extension of the RMDL principle in the context of universal intelligence agents is considered, for which introduction of representations is shown to be an unavoidable metaheuristic and a step toward efficient general intelligence. Hierarchical representations and model optimization with the use of informationtheoretic interpretation of the adaptive resonance are also discussed.