Engineering General Intelligence, Part 2

TL;DR: This article provides the first full motivation, presentation and analysis of Sigma, along with a diversity of more specific results that have been generated during its development.

TL;DR: An introduction to MECA, the Multipurpose Enhanced Cognitive Architecture, a cognitive architecture developed by the research group and implemented in the Java language, which promotes an hybridism of SOAR.

TL;DR: The problem of unsupervisedly inducing a formal grammar for any language, using the Link Grammar paradigm, from unannotated parses also obtained without supervision from an input corpus is explored.

TL;DR: In “Constructing a Language,” Tomasello presents a contrasting theory of how the child acquires language: It is not a universal grammar that allows for language development, but two sets of cognitive skills resulting from biological/phylogenetic adaptations are fundamental to the ontogenetic origins of language.

TL;DR: A general, trainable system for object detection in unconstrained, cluttered scenes that derives much of its power from a representation that describes an object class in terms of an overcomplete dictionary of local, oriented, multiscale intensity differences between adjacent regions, efficiently computable as a Haar wavelet transform.

TL;DR: Tomasello as discussed by the authors presented a synthesis of that work as well as an exposition of an account of language development, which provides a thought-provoking challenge to the generative enterprise.