AGI Projects

From OpenCog

This page lists some AGI systems and projects.

It's not intended as a complete catalog, nor as an endorsement by anybody of the approaches or ideas that happened to be mentioned here. (And, the approaches listed here generally have nothing to do with OpenCog, although OpenCog Foundation is hosting this wiki page.)

For a larger, but not editable (and also not nearly complete), list of AGI-oriented cognitive architectures, see the Comparative Repository of Cognitive Architectures created by Alexei Samsonovich based on inputs from many others.

See the page AGI_Wiki for more generic AGI discussion, not necessarily about a specific project or system.

See the Mind Ontology AGI Projects page for an older but more detailed description of some AGI systems.

If you are an AGI researcher with an approach that isn't listed here, feel free to fill in yours in the following format:

Researcher name or project name.
Summary (should not exceed 1000 characters).
Link to more info: wiki page, project homepage, publications, etc.

This specific page is not the place for a long description of your project. However, you are welcome to create another page on the OpenCog wiki site, linked from your project's entry on this page, and put lots of information about your project there.

An integrative architecture designed to embody synergies between multiple learning algorithms and representations. Current work focuses on controlling a learning agent in a virtual world, with robotics work on the horizon.

An Embodied Artificial Life approach to evolution of an AGI, focusing on ethology and maze-running as a measuring stick for progress.

Russell Wallacee
Turn programs into procedural knowledge, via logical reasoning about code, guided by heuristics both hand coded and automatically learned.

Matt Mahoney
AGI = lots of narrow specialists + a distributed index for routing messages to the right experts + economic incentives to be useful in a decentralized, hostile market.
Language model evaluation and cost estimation by text compression.

Arthur T. Murray
Implement spreading activation as AI Minds in Forth and JavaScript.
First Working AGI in JavaScript and Forth.
Ghost AGI in Perl.

Will Pearson
Designing an architecture to allow experimental code creation to not interfere with other parts of the system, while allowing the parts of the system to change in purposeful fashion. -Note not a full AGI approach but a prerequisite project.

YKY (Yan King Yin)
higher-order logic + fuzzy-probabilistic calculus + inductive learning.

Joseph Henry
An architecture based on replicating human cognitive abilities through direct engineering of self-modifying discrete task modules, held together via a highly general knowledge representation language.