AGI 17

Talks sessions will have 15 minute oral presentations, followed by a 30 minute panel discussion. There will be a “lightning talk” session for poster presenters, with a 5 minute presentation for each poster.

The papers in each session are:

Architectures (Chair: Jordi Bieger)

• From Abstract Agents Models to Real-World AGI Architectures (Ben Goertzel)
• A Formal Model of Cognitive Synergy (Ben Goertzel)
• Generic Animats (Claes Strannegård, Nils Svangård, Joscha Bach and Bas Steunebrink)
• Self-Awareness and Self-Control in NARS (Pei Wang, Xiang Li and Patrick Hammer)
• DSO Cognitive Architecture: Unified Reasoning with Integrative Memory using Global Workspace Theory (Khin Hua Ng, Zhiyuan Du and Gee Wah Ng)

Mathematical foundations (Chair: Tom Everitt)

• A general (category theory) principle for general intelligence: duality (adjointness) (Steven Phillips)
• Abstract Representations and Generalized Frequent Pattern Discovery (Eray Ozkural)
• On hierarchical compression and power laws in nature (Arthur Franz)
• From First-Order Logic to Assertional Logic (Yi Zhou)

Algorithms (Chair: Cosmo Harrigan)

• Genetic algorithms with DNN-based trainable crossover as an example of partial specialization of general search (Alexey Potapov and Sergey Rodionov)
• Deductive and Analogical Reasoning on a Semantically Embedded Knowledge Graph (Douglas Summers-Stay)
• Computational neuroscience offers hints for more general machine learning (David Rawlinson and Gideon Kowadlo)

Safety and Philosophy (Chair: Claes Strannegård)

• What People Say? Web-based Casuistry for Artificial Morality Experiments (Rafal Rzepka and Kenji Araki)
• Malevolent Cyborgization (Nadisha-Marie Aliman)
• A Priori Modeling of Information and Intelligence (Marcus Abundis)
• A Game-Theoretic Analysis of The Off-Switch Game (Tobias Wängberg, Mikael Böörs, Elliot Catt, Tom Everitt and Marcus Hutter)
• The Future of Artificial Intelligence and Society (Marcus Hutter) (video)

Human Cognition and Understanding (Chair: Pei Wang)

• An Information-Theoretic Predictive Model for the Accuracy of AI Agents Adapted From Psychometrics (Nader Chmait, David Dowe, Yuan-Fang Li and David Green)
• Understanding and Common Sense: Two Sides of the Same Coin? (Kristinn Thórisson and David Kremelberg)
• The Pedagogical Pentagon: A Conceptual Framework for Artificial Pedagogy (Jordi Bieger, Kristinn R. Thórisson and Bas Steunebrink)
• Bandit Models of Human Behavior: Reward Processing in Mental Disorders (Djallel Bouneffouf, Irina Rish and Guillermo Cecchi)

Posters

• Generating Single Subject Activity Videos as a Sequence of Actions using 3D Convolutional Generative Adversarial Networks (Ahmad Arinaldi and Mohamad Ivan Fanany)
• One-Shot Ontogenetic Learning in Biomedical Datastreams (John Kalantari and Michael Mackey)
• The MaRz Algorithm: Towards an Artificial General Episodic Learner (Christian Rodriguez, Giselle Marston, William Goolkasian, Ashley Rosenberg and Andrew Nuxoll)
• Analyzing Human Decision Making Process with Intention Estimation using Cooperative Pattern Task (Kota Itoda, Norifumi Watanabe and Yoshiyasu Takefuji)
• Pursuing Fundamental Advances in Human Reasoning (Tim van Gelder and Richard de Rozario)
• Public Policy on AGI (Gary Lea)

Understanding Understanding workshop (video playlist)

• 10:00-10:15 Registration
• 10:15-10:20 Welcome by David Kremelberg
• 10:20-10:55 Target talks, comments and discussion: “Understanding as Conceptualizing” by Pei Wang (video)
• 10:55-11:30 Target talks, comments and discussion: “Do Machines Understand? A Short
  Review of Understanding: Common Sense in Artificial Intelligence” by Kris Thorisson and
  David Kremelberg (video)
• “Necessary Ingredients for Understanding ing AI” by David Kremelberg (video)
• “How to Define and Measure Understanding” by Kris Thorisson (video)
• 11:30-11:50 Invited talk: Tom Everitt: “AI Safety and Understanding” (video)

Special topics

• 1:00-1:30 Machine Understanding: Object and Situation. Moderators: Dave and Kris (video)
• 1:30-2:00 Machine Understanding: Mechanisms for Question and Answering. Moderators: Kris and Pei (video)
• 2:00-2:30 Machine Understanding: Translation and Conversation. Moderators: Dave and Pei (video)
• 2:30-3:00 Machine Understanding: Goal-Achievement and Artwork. Moderators: Dave and Kris (video)

AGI17 Unconference and Wrap-up (video)

• AI in Society – Ethics, Safety, Industry and Governance (video)