Draft of an introduction to the research field at the interface between statistical physics, theretical computer science/discrete mathematics, and coding/information theory.

"According to the theory, consciousness corresponds to the capacity of a system to integrate information."

Giulio Tononi on how his theory of consciousness tries to explain the fundamental properties a system must have to be able to generate a conscious experience.

Argues that thermodynamic entropy can't be identified with the information-theoretic uncertainty of an (ideal) observer’s subjective distribution over a system’s microstates.

Provides a unified view on Information theory, Bayesian probability theory and machine learning.

'volume itself is illusory and the universe is really a hologram which is isomorphic to the information "inscribed" on the spherical surface of its boundary. [..] the fundamental particle is a bit (1 or 0) of information.'

Introduces 'predictive information', a measure of the mutual information between the past and the future of a time series. Unique if all observers with prior distributions limited to local interactions need to arrive at the same measure.

The ability to substantially predict the future of morality would be a strong argument against morality changes being due to info we learn, just as the ability to predict future stock prices would argue against stock price changes being due to info.

The major theme of the thesis is to develop a mathematical foundation of Artificial Intelligence and, more specifically, to develop a theory for rational agents acting optimally in any environment.

Soweit fürs maschinelle Lernen relevant. Stichwortartige Beilage zur Vorlesung "Maschinelles Lernen II" (SS 2005).

A video presentation that artfully presents the impending effects of globalization and the exponentially growing development of new technologies to describe the future.

A formalization of Occam's Razor in which the best hypothesis for a given set of data is the one that leads to the largest compression of the data. Computable!

Great introduction to algorithmic information theory. Explains Kolmogorov complexity, Solomonoff probability, Levins Kt-complexity, "Martin-Loef" randomness, ...

A detailed introduction to the main techniques of algorithmic information theory.

The Bekenstein bound imposes a limit on the entropy S or information that can be contained within a three-dimensional volume. (One reason why hypercomputing proposals fail.)

"People don't read the news because that it is useful; they read it to show how much they know and how well they can analyze it."

A situation in which every subsequent actor, based on the observations of others, makes the same choice independent of his/her private signal.

If a theorem contains more information than a given set of axioms, then it is impossible for the theorem to be derived from the axioms. This suggests that the incompleteness phenomenon discovered by Gödel is natural and widespread [..].

The Kolmogorov complexity of an object such as a piece of text is a measure of the computational resources needed to specify the object.