Artificial General Intelligence: 6th International by Ahmed M. H. Abdel-Fattah, Ulf Krumnack, Kai-Uwe Kühnberger

By Ahmed M. H. Abdel-Fattah, Ulf Krumnack, Kai-Uwe Kühnberger (auth.), Kai-Uwe Kühnberger, Sebastian Rudolph, Pei Wang (eds.)

This publication constitutes the refereed complaints of the sixth foreign convention on man made basic Intelligence, AGI 2013, held in Beijing, China, in July/August 2013. The 23 papers (17 complete papers, three technical communications, and three distinct consultation papers) have been conscientiously reviewed and chosen from quite a few submissions. the amount collects the present study endeavors dedicated to enhance formalisms, algorithms, and versions, in addition to structures which are particular at normal intelligence. just like the predecessor AGI meetings, researchers proposed diversified methodologies and strategies to be able to bridge the space among varieties of really good intelligence and normal intelligence.

Show description

Read or Download Artificial General Intelligence: 6th International Conference, AGI 2013, Beijing, China, July 31 – August 3, 2013 Proceedings PDF

Best general books

Handbook of Psychology, Experimental Psychology

Contains verified theories and state of the art advancements. provides the paintings of a world team of specialists. provides the character, foundation, implications, and destiny process significant unresolved matters within the zone.

Reducing Benzodiazepine Consumption: Psychological Contributions to General Practice

Spurred by way of studies in 1980 detailing the ineffectiveness of long term remedy with benzodiazepines, the authors of this quantity all started a learn to enquire the explanations at the back of the habit, speedy adopting a mental method of remedy. In checking out the efficacy of hysteria administration thoughts in its place to benzodiazepine use, Drs.

Extra resources for Artificial General Intelligence: 6th International Conference, AGI 2013, Beijing, China, July 31 – August 3, 2013 Proceedings

Example text

Verbrugge, R. ) Proc. of the Workshop on Reasoning About Other Minds (RAOM 2011). CEUR Workshop Proceedings, vol. 751, pp. 20–31. org (July 2011) 20. : Towards a Domain-Independent Computational Framework for Theory Blending. AAAI Technical Report of the AAAI Fall 2011 Symposium on Advances in Cognitive Systems, pp. 210–217 (2011) 21. : Theory Blending as a Framework for Creativity in Systems for General Intelligence. , Goertzel, B. ) Theoretical Foundations of AGI. Atlantis Press (2012) 22. : Approximation Algorithms.

However, when MOSES tasks are launched automatically via the OpenCog scheduler based on an OpenCog agent’s goals, there is no opportunity for the clever choice of feature selection heuristics based on the particular data involved. And crude feature selection heuristics based on elementary statistics, are often insufficiently effective, as they rule out too many valuable features (and sometimes rule out the most critical features). In this context, having a variant of MOSES that can sift through the scope of possible features in the course of its learning is very important.

Other measures than mutual information may be used here as well. The LIFES process doesn’t necessarily obviate the need for up-front feature selection. What it does, is prevent up-front feature selection from limiting the ultimate feature usage of the learning algorithm. It allows the initially selected features to be used as a rough initial guide to learning – and for the candidates learned using these initial features, to then be refined and improved using additional features chosen opportunistically along the learning path.

Download PDF sample

Rated 4.67 of 5 – based on 49 votes