Universal Artificial Intelligence: Sequential Decisions Based On Algorithmic Probability
Universal Artificial Intelligence: Sequential Decisions Based On Algorithmic Probability
Vision: A Computational Investigation into the Human Representation and Processing of Visual Information
A computational approximation to the AIXI model
Proceedings of the 2008 conference on Artificial General Intelligence 2008: Proceedings of the First AGI Conference
Learning Deep Architectures for AI
Foundations and Trends® in Machine Learning
Compression and intelligence: social environments and communication
AGI'11 Proceedings of the 4th international conference on Artificial general intelligence
| Hi-index | 0.00 |
Solomonoff induction is known to be universal, but incomputable. Its approximations, namely, the Minimum Description (or Message) Length (MDL) principles, are adopted in practice in the efficient, but non-universal form. Recent attempts to bridge this gap leaded to development of the Representational MDL principle that originates from formal decomposition of the task of induction. In this paper, possible extension of the RMDL principle in the context of universal intelligence agents is considered, for which introduction of representations is shown to be an unavoidable meta-heuristic and a step toward efficient general intelligence. Hierarchical representations and model optimization with the use of information-theoretic interpretation of the adaptive resonance are also discussed.