Sketch of an AGI architecture with illustration

András Lorincz, Zoltán R. Bárdosi, Dániel Takács

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Here we present a framework for AGI inspired by knowledge about the only working prototype: the brain. We consider the neurobiological findings as directives. The main algorithmic modules are defined and solutions for each subtasks are given together with the available mathematical (hard) constraints. The main themes are compressed sensing, factor learning, independent process analysis and low dimensional embedding for optimal state representation to be used by a particular RL system that can be integrated with a robust controller. However, the blending of the suggested partial solutions is not a straightforward task. Nevertheless we start to combine these modules and illustrate their working on a simulated problem. We will discuss the steps needed to complete the integration.

Original languageEnglish
Title of host publicationArtificial General Intelligence - Proceedings of the Third Conference on Artificial General Intelligence, AGI 2010
Pages85-90
Number of pages6
Publication statusPublished - Jul 5 2010
Event3rd Conference on Artificial General Intelligence, AGI 2010 - Lugano, Switzerland
Duration: Mar 5 2010Mar 8 2010

Publication series

NameArtificial General Intelligence - Proceedings of the Third Conference on Artificial General Intelligence, AGI 2010

Other

Other3rd Conference on Artificial General Intelligence, AGI 2010
CountrySwitzerland
CityLugano
Period3/5/103/8/10

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Sketch of an AGI architecture with illustration'. Together they form a unique fingerprint.

  • Cite this

    Lorincz, A., Bárdosi, Z. R., & Takács, D. (2010). Sketch of an AGI architecture with illustration. In Artificial General Intelligence - Proceedings of the Third Conference on Artificial General Intelligence, AGI 2010 (pp. 85-90). (Artificial General Intelligence - Proceedings of the Third Conference on Artificial General Intelligence, AGI 2010).