Artificial General Intelligence: 8th International Conference

Artificial General Intelligence: 8th International Conference, AGI 2015, AGI 2015, Berlin, Germany, July 22-25, 2015, Proceedings (Lecture Notes in Computer Science)

This book constitutes the refereed proceedings of the 8th International Conference on Artificial General Intelligence, AGI 2015, held in Berlin, Germany in July 2015. The 41 papers were carefully reviewed and selected from 72 submissions. 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. 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.

Table of Contents

Chapter 1. Modeling Motivation in MicroPsi 2
Chapter 2. Genetic Programming on Program Traces as an Inference Engine for Probabilistic Languages
Chapter 3. Scene Based Reasoning
Chapter 4. Anchoring Knowledge in Interaction: Towards a Harmonic Subsymbolic/Symbolic Framework and Architecture of Computational Cognition
Chapter 5. Safe Baby AGI
Chapter 6. Observation, Communication and Intelligence in Agent-Based Systems
Chapter 7. Reflective Variants of Solomonoff Induction and AIXI
Chapter 8. Are There Deep Reasons Underlying the Pathologies of Today’s Deep Learning Algorithms?
Chapter 9. Speculative Scientific Inference via Synergetic Combination of Probabilistic Logic and Evolutionary Pattern Recognition
Chapter 10. Stochastic Tasks: Difficulty and Levin Search
Chapter 11. Instrumental Properties of Social Testbeds
Chapter 12. Towards Human-Level Inductive Functional Programming
Chapter 13. Anytime Bounded Rationality
Chapter 14. Ultimate Intelligence Part I: Physical Completeness and Objectivity of Induction
Chapter 15. Towards Emotion in Sigma: From Appraisal to Attention
Chapter 16. Inferring Human Values for Safe AGI Design
Chapter 17. Two Attempts to Formalize Counterpossible Reasoning in Deterministic Settings
Chapter 18. Bounded Cognitive Resources and Arbitrary Domains
Chapter 19. Using Localization and Factorization to Reduce the Complexity of Reinforcement Learning
Chapter 20. Towards Flexible Task Environments for Comprehensive Evaluation of Artificial Intelligent Systems and Automatic Learners
Chapter 21. Assumptions of Decision-Making Models in AGI
Chapter 22. Issues in Temporal and Causal Inference
Chapter 23. The Space of Possible Mind Designs
Chapter 24. A Definition of Happiness for Reinforcement Learning Agents
Chapter 25. Expression GraphsUnifying Factor Graphs and Sum-Product Networks
Chapter 26. Toward Tractable Universal Induction Through Recursive Program Learning
Chapter 27. How Can Cognitive Modeling Benefit from Ontologies? Evidence from the HCI Domain
Chapter 28. C-Tests Revisited: Back and Forth with Complexity
Chapter 29. A New View on Grid Cells Beyond the Cognitive Map Hypothesis
Chapter 30. Programming Languages and Artificial General Intelligence
Chapter 31. From Specialized Syntax to General Logic: The Case of Comparatives
Chapter 32. Decision-Making During Language Understanding by Intelligent Agents
Chapter 33. Plan Recovery in Reactive HTNs Using Symbolic Planning
Chapter 34. Optimization Framework with Minimum Description Length Principle for Probabilistic Programming
Chapter 35. Can Machines Learn Logics?
Chapter 36. Comparing Computer Models Solving Number Series Problems
Chapter 37. Emotional Concept Development
Chapter 38. The Cyber-Physical System Approach Towards Artificial General Intelligence: The Problem of Verification
Chapter 39. Analysis of Types of Self-Improving Software
Chapter 40. On the Limits of Recursively Self-Improving AGI
Chapter 41. Gödel Agents in a Scalable Synchronous Agent Framework