Learning, inference, prediction, complex systems, evolution, ... – feels like Christmas!

"our dancing in clubs will alter the music which will alter our dancing, and the music and the visualisation/dancing will be translations of one another, and no way to tell which is first, because none is."

Convinced me that Bayesian inference over hierarchies of flexibly structured representations is a good model of human inductive learning.

AutoCore is a virtual machine for general purpose evolutionary computation based on recent advances in digital artificial life pioneered by the academic community for the study of theoretical evolutionary biology and ecology.

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.

This course tries to connect quantum computing to the wider intellectual world: The measurement problem, computational complexity, cryptography, Gödel, Turing, Penrose, randomness, ...

Gödel machines are self-referential universal problem solvers making provably optimal self- improvements.

Participants: Eliezer Yudkowsky, Jeff Medina, Dr. Karl H. Pribram, Ari Heljakka, Dr. Hugo de Garis.

What would it be like to find meaning and order in everything you saw?

Eurisko is a program written by Doug Lenat. It consists of heuristics, i.e. rules of thumb, including heuristics describing how to use and change its heuristics. It was applied to a number of domains with surprising success.