Extending Universal Intelligence Models with Formal Notion of Representation
نویسندگان
چکیده
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.
منابع مشابه
Toward a Formal Characterization of Real-World General Intelligence
Two new formal definitions of intelligence are presented, the ”pragmatic general intelligence” and ”efficient pragmatic general intelligence.” Largely inspired by Legg and Hutter’s formal definition of ”universal intelligence,” the goal of these definitions is to capture a notion of general intelligence that more closely models that possessed by humans and practical AI systems, which combine an...
متن کاملCognitive Bias for Universal Algorithmic Intelligence
Existing theoretical universal algorithmic intelligence models are not practically realizable. More pragmatic approach to artificial general intelligence is based on cognitive architectures, which are, however, non-universal in sense that they can construct and use models of the environment only from Turingincomplete model spaces. We believe that the way to the real AGI consists in bridging the...
متن کاملOn Designing Situated Ontologies for Knowledge Sharing in Communities of Practice
Ontologies are everywhere in today’s discussion of knowledge related technologies, from the vision of an upcoming Semantic Web to routine organizational knowledge management. While some still deplore the proliferation of a formerly august philosophical term in increasingly mundane applications, others try hard to make sense of an emerging concept in systems design. The notion of (formal) ontolo...
متن کاملUNIVERSAL COMPACTIFICATIONS OF TRANSFORMATION SEMIGROUPS
We extend the notion of semigroup compactification to the class of transformation semigroups, and determine the compactifications which are universal with respect to some topological properties.
متن کاملA Joint Semantic Vector Representation Model for Text Clustering and Classification
Text clustering and classification are two main tasks of text mining. Feature selection plays the key role in the quality of the clustering and classification results. Although word-based features such as term frequency-inverse document frequency (TF-IDF) vectors have been widely used in different applications, their shortcoming in capturing semantic concepts of text motivated researches to use...
متن کامل