The Open Cog Framework -- Knowledge Representation Using the Atomspace -- Representing Procedural Knowledge -- Emotion, Motivation, Attention and Control -- Attention Allocation -- Economic Goal and Action Selection -- Integrative Procedure Evaluation -- Perceptual and Motor Hierarchies -- Integrating Cog Prime with a Compositional Spatiotemporal Deep Learning Network -- Making DeSTIN Representationally Transparent -- Bridging the Symbolic/Subsymbolic Gap -- Procedure Learning as Program Learning -- Learning Procedures via Imitation, Reinforcement and Correction -- Procedure Learning via Adaptively Biased Hillclimbing -- Probabilistic Evolutionary Procedure Learning -- Probabilistic Logic Networks -- Spatio-Temporal Inference -- Adaptive, Integrative Inference Control -- Pattern Mining. -- Speculative Concept Formation -- Dimensional Embedding -- Mental Simulation and Episodic Memory -- Integrative Procedure Learning -- Map Formation -- Communication Between Artificial Minds -- Natural Language Comprehension -- Language Learning via Unsupervised Corpus Analysis -- Natural Language Generation -- Embodied Language Processing -- Natural Language Dialogue -- Summary of Argument for the Cog Prime Approach
Summary
The work outlines a detailed blueprint for the creation of an Artificial General Intelligence system with capability at the human level and ultimately beyond, according to the Cog Prime AGI design and the Open Cog software architecture
