One Decade of Universal Artificial Intelligence
@article{Hutter2012OneDO, title={One Decade of Universal Artificial Intelligence}, author={Marcus Hutter}, journal={ArXiv}, year={2012}, volume={abs/1202.6153} }
The first decade of this century has seen the nascency of the first mathematical theory of general artificial intelligence. This theory of Universal Artificial Intelligence (UAI) has made significant contributions to many theoretical, philosophical, and practical AI questions. In a series of papers culminating in book (Hutter, 2005), an exciting sound and complete mathematical model for a super intelligent agent (AIXI) has been developed and rigorously analyzed. While nowadays most AI…
41 Citations
An Overview of Approaches Evaluating Intelligence of Artificial Systems
- Computer Science
- 2018
The Algorithmic Intelligence Quotient test, derived from Universal Intelligence definition, is currently the most suitable candidate for a practical intelligence evaluation method of artificial systems, although the test has several known limitations.
The search for (artificial) intelligence, in capitalism
- Art
- 2019
Artificial intelligence is being touted as a new wave of machinic processing and productive potential. Building on concepts starting with the invention of the term artificial intelligence in the…
Can Intelligence Explode?
- Computer ScienceArXiv
- 2012
This course will provide a more careful treatment of what intelligence actually is, separate speed from intelligence explosion, compare what super-intelligent participants and classical human observers might experience and do, discuss immediate implications for the diversity and value of life, consider possible bounds on intelligence, and contemplate intelligences right at the singularity.
The mirror for (artificial) intelligence: Working in whose reflection?
- Art
- 2019
The discussion paper argues that a series of machinic and technological invention and related experiments show how machines facilitate not only the processes of normalization of what are considered intelligent behaviours, via both human and machinic intelligence, but also facilitate and enable the integration of autonomous machines into everyday work and life.
The mirror for (artificial) intelligence in capitalism
- Art
- 2020
‘The mirror for (artificial) intelligence in capitalism’ expands on the historical episodes outlined in the article by Engster and Moore in the current Special Issue, to develop the historical…
Foundations of Induction
- Philosophy
- 2011
Solomonoff’s formal, general, complete, and essentially unique theory of universal induction and prediction, rooted in algorithmic information theory and based on the philosophical and technical ideas of Ockham, Epicurus, Bayes, Turing, and Kolmogorov, essentially constitutes a conceptual solution to the induction problem.
Subjective Reality and Strong Artificial Intelligence
- Computer ScienceArXiv
- 2013
This paper formulate the model of the perception of external world which may be used for the description of perceptual activity of intelligent beings and shows how the methodology of subjective reality may be use for the creation of different types of Strong AI systems.
Strengths and potential of the SP theory of intelligence in general, human-like artificial intelligence
- Computer Science
- 2017
There are reasons to believe that a mature version of the SP system may attain full GHLAI in diverse aspects of intelligence and in the representation of diverse kinds of knowledge.
The Foundations of Solomonoff Prediction
- Philosophy
- 2013
R.J. Solomonoff’s theory of Prediction assembles notions from information theory, confirmation theory and computability theory into the specification of a supposedly all-encompassing objective method…
References
SHOWING 1-10 OF 99 REFERENCES
Universal Artificial Intelligence
- Computer ScienceTexts in Theoretical Computer Science An EATCS Series
- 2005
UAI is an increasingly well-studied foundational theory for artificial intelligence, based on ancient principles in the philosophy of science and modern developments in information and probability theory, that provides a theoretically optimal agent AIXI and principled ideas for constructing practical autonomous agents.
Universal Intelligence: A Definition of Machine Intelligence
- Computer ScienceMinds and Machines
- 2007
A number of well known informal definitions of human intelligence are taken, and mathematically formalised to produce a general measure of intelligence for arbitrary machines that formally captures the concept of machine intelligence in the broadest reasonable sense.
An Approximation of the Universal Intelligence Measure
- Computer ScienceAlgorithmic Probability and Friends
- 2011
This paper studies the practical issues involved in developing a real-world UIM-based performance metric and develops a prototype implementation which is used to evaluate a number of different artificial agents.
Logics in Artificial Intelligence
- PhilosophyLecture Notes in Computer Science
- 1994
This book's goal, to serve as an elementary text and reference work on the applications of nonstandard logics to artificial intelligence, is somewhat more restrictive than what was inferred from the rifle, namely uses of logic in AI.
Theoretical Foundations of Artificial General Intelligence
- EducationAtlantis Thinking Machines
- 2012
This book is a collection of writings by active researchers in the field of Artificial General Intelligence, on topics of central importance in the field. Each chapter focuses on one theoretical…
Can Intelligence Explode?
- Computer ScienceArXiv
- 2012
This course will provide a more careful treatment of what intelligence actually is, separate speed from intelligence explosion, compare what super-intelligent participants and classical human observers might experience and do, discuss immediate implications for the diversity and value of life, consider possible bounds on intelligence, and contemplate intelligences right at the singularity.
A Philosophical Treatise of Universal Induction
- PhilosophyEntropy
- 2011
The case for Solomonoff Induction is argued, a formal inductive framework which combines algorithmic information theory with the Bayesian framework and how this approach addresses many issues that have plagued other inductive systems, such as the black ravens paradox and the confirmation problem.
Open Problems in Universal Induction & Intelligence
- Computer ScienceAlgorithms
- 2009
The state of the art in universal induction and its extension to universal intelligence is described and the state-of-the-art is described only in passing and the reader is referred to the literature.
Measuring universal intelligence: Towards an anytime intelligence test
- Computer ScienceArtif. Intell.
- 2010