Universal Artificial Intelligence: Sequential Decisions Based On Algorithmic Probability

by Marcus Hutter

Personal motivation. The dream of creating artificial devices that reach or outperform human inteUigence is an old one. It is also one of the dreams of my youth, which have never left me. What makes this challenge so interesting? A solution would have enormous implications on our society, and there are reasons to believe that the AI problem can be solved in my expected lifetime. So, it's worth sticking to it for a lifetime, even if it takes 30 years or so to reap the benefits. The AI problem. The science of artificial intelligence (AI) may be defined as the construction of intelligent systems and their analysis. A natural definition of a system is anything that has an input and an output stream. Intelligence is more complicated. It can have many faces like creativity, solving prob­ lems, pattern recognition, classification, learning, induction, deduction, build­ ing analogies, optimization, surviving in an environment, language processing, and knowledge. A formal definition incorporating every aspect of intelligence, however, seems difficult. Most, if not all known facets of intelligence can be formulated as goal driven or, more precisely, as maximizing some utility func­ tion. It is, therefore, sufficient to study goal-driven AI; e. g. the (biological) goal of animals and humans is to survive and spread. The goal of AI systems should be to be useful to humans.

Genres: Artificial Intelligence, Computer Science, Textbooks

298 pages, Hardcover

First published January 1, 2004

Reviews

[Jovany Agathe · Rating 5 out of 5]

This book differs from most books on the theoretical formulations of artificial intelligence in that it attempts to give a more rigorous accounting of machine learning and to rank machines according to their intelligence. To accomplish this ranking, the author introduces a concept called `universal artificial intelligence,' which is constructed in the context of algorithmic information theory. In fact, the book could be considered to be a formulation of artificial intelligence from the standpoint of algorithmic information theory, and is strongly dependent on such notions as Kolmogorov complexity, the Solomonoff universal prior, Martin-Lof random sequences and Occam's razor. These are all straightforward mathematical concepts with which to work with, the only issue for researchers being their efficacy in giving a useful notion of machine intelligence.

[Kevin Doran · Rating 2 out of 5]

Note: not finished.

Has anyone ever read all of this book? Properly? I'm skeptical.

Anyway, a note to the author/publisher: please increase the line-spacing. The symbols on one line are so close to the next line that you have to double-check which line they are part of.

[Daanish Shabbir]

This is impossible to read (unless u do a phd with Marcus?)! but I know now the basics of AIXI