A Philosophical Treatise of Universal Induction

  title={A Philosophical Treatise of Universal Induction},
  author={Samuel Rathmanner and Marcus Hutter},
Understanding inductive reasoning is a problem that has engaged mankind for thousands of years. This problem is relevant to a wide range of fields and is integral to the philosophy of science. It has been tackled by many great minds ranging from philosophers to scientists to mathematicians, and more recently computer scientists. In this article we argue the case for Solomonoff Induction, a formal inductive framework which combines algorithmic information theory with the Bayesian framework… Expand

Paper Mentions

Universal Induction and Optimisation: No Free Lunch
This thesis adapts universal induction to optimisation, and investigates its performance by putting it against the so-called No Free Lunch theorems, which show that under certain conditions, effective optimisation is impossible. Expand
Philosophy of science and information
Of all the sub-disciplines of philosophy, the philosophy of science has perhaps the most privileged relationship to information theory. This relationship has been forged through a common interest inExpand
Don't choose theories: Normative inductive reasoning and the status of physical theories
Evaluating theories in physics used to be easy. Our theories provided very distinct predictions. Experimental accuracy was so small that worrying about epistemological problems was not necessary.Expand
Foundations of Induction
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. Expand
Natural Descriptions and Anthropic Bias: Extant Problems In Solomonoff Induction
The theory of Solomonoff induction, which combines algorithmic information theory and Bayesian inference, has been suggested as a solution to the philosophical problem of induction and an idealisation of the scientific method. Expand
Towards common-sense reasoning via conditional simulation: legacies of Turing in Artificial Intelligence
This work describes a computational formalism centered around a probabilistic Turing machine called QUERY, which captures the operation of Probabilistic conditioning via conditional simulation and demonstrates how the QUERY abstraction can be used to cast common-sense reasoning as probabilism inference in a statistical model of observations and the uncertain structure of the world that generated that experience. Expand
One Decade of Universal Artificial Intelligence
This article attempts to gently introduce a very theoretical, formal, and mathematical subject, and discusses philosophical and technical ingredients, traits of intelligence, some social questions, and the past and future of UAI. Expand
An Evolutionary Argument for a Self-Explanatory, Benevolent Metaphysics
Abstract: In this paper, a metaphysics is proposed that includes everything that can be represe nted by a well -founded multiset. It is shown that this metaphysics, apart from being selfExpand
Universal Algorithmic Ethics
This paper proposes a novel research direction for algorithmic probability theory, which now allows to formalize philosophical questions about concepts such as the simulation argument, personalExpand
The Relativity of Induction
The core problem of generalization is explored and it is shown that long-accepted Occam's razor and parsimony principles are insufficient to ground learning, and a set of relativistic principles are derived that yield clearer insight into the nature and dynamics of learning. Expand


Probability theory: the logic of science
This is a remarkable book by a remarkable scientist. E. T. Jaynes was a physicist, principally theoretical, who found himself driven to spend much of his life advocating, defending and developing aExpand
An Introduction to Kolmogorov Complexity and Its Applications
  • Ming Li, P. Vitányi
  • Computer Science, Psychology
  • Texts and Monographs in Computer Science
  • 1993
The book presents a thorough treatment of the central ideas and their applications of Kolmogorov complexity with a wide range of illustrative applications, and will be ideal for advanced undergraduate students, graduate students, and researchers in computer science, mathematics, cognitive sciences, philosophy, artificial intelligence, statistics, and physics. Expand
Dutch Bookies and Money Pumps
C ONCLUSIVE arguments in philosophy are rare, so any such argument we find we prize. If it is not only conclusive but clever, all the better for it. The Dutch book arguments of the theory ofExpand
Open Problems in Universal Induction & Intelligence
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. Expand
Universal Intelligence: A Definition of Machine Intelligence
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. Expand
The theory that would not die
In the early 1730sThomas Bayes (1701?–1761)was appointed minister at the Presbyterian Meeting House on Mount Sion, Tunbridge Wells, a town that had developed around the restorative chalybeate springExpand
Contemporary debates in philosophy of science
Notes on Contributors.Preface.Introduction: What is the Philosophy of Science?.Part I: Do Thought Experiments Transcend Empiricism?.1. Why Thought Experiments Transcend Empiricism: James Robert BrownExpand
On Universal Prediction and Bayesian Confirmation
  • Marcus Hutter
  • Computer Science, Mathematics
  • Theor. Comput. Sci.
  • 2007
It is shown that Solomonoff’s model possesses many desirable properties: strong total and future bounds, and weak instantaneous limits, and, in contrast to most classical continuous prior densities, it has no zero p(oste)rior problem. Expand
A Complete Theory of Everything (Will Be Subjective)
The suggested principle is extended to morepractical (partial, approximate, probabilistic, parametric) world models (rather than theories of everything) and provided a justification of Ockham’s razor, and criticize the anthropic principle, the doomsday argument, the no free lunch theorem, and the falsi fiability dogma. Expand
A Computer Scientist's View of Life, the Universe, and Everything
Is the universe computable? If so, it may be much cheaper in terms of information requirements to compute all computable universes instead of just ours. I apply basic concepts of KolmogorovExpand