Artificial General Intelligence

This book constitutes the refereed proceedings of the 7th International Conference on Artificial General Intelligence, AGI 2014, held in Quebec City, QC, Canada, in August 2014. The 22 papers and 8 posters were carefully reviewed and selected from 65 submissions. Researchers have recognized the necessity of returning to the original goals of the field by treating intelligence as a whole. Increasingly, there is a call for a transition back to confronting the more difficult issues of "human-level intelligence" and more broadly artificial general intelligence. AGI research differs from the ordinary AI research by stressing on the versatility and wholeness of intelligence and by carrying out the engineering practice according to an outline of a system comparable to the human mind in a certain sense. The AGI conference series has played and continues to play, a significant role in this resurgence of research on artificial intelligence in the deeper, original sense of the term of "artificial intelligence". The conferences encourage interdisciplinary research based on different understandings of intelligence and exploring different approaches.

Inhalt

Agent Architectures.- Autonomy.- Benchmarks and Evaluation.- Cognitive Modeling.- Collaborative Intelligence.- Creativity.- Distributed AI.- Formal Models of General Intelligence.- Implications of AGI for Society, Economy and Ecology.- Integration of Different Capabilities.- Knowledge Representation for General Intelligence.- Languages, Specification Approaches and Toolkits.- Learning, and Learning Theory.- Motivation, Emotion and Affect.- Multi-Agent Interaction.- Natural Language Understanding.- Neural-Symbolic Processing.- Perception and Perceptual Modeling.- Philosophy of AGI.- Reasoning, Inference and Planning.- Reinforcement Learning.- Robotic and Virtual Embodiment.- Simulation and Emergent Behavior.- Solomonoff Induction.