Artificial General Intelligence through Large-Scale, Multimodal Bayesian Learning

Abstract. An artificial system that achieves human-level performance on opendomain tasks must have a huge amount of knowledge about the world. We argue that the most feasible way to construct such a system is to let it learn from the large collections of text, images, and video that are available online. More specifically, the system should use a Bayesian probability model to construct hypotheses about both specific objects and events, and general patterns that explain the observed data. Keywords. probabilistic model, architecture, knowledge acquisition

• Type: Conference
• Year: 2008
• Where: AGI
• Authors: Brian Milch
• Keywords: AGI 2008, Artificial Intelligence, Bayesian Probability Model, Feasible Way, Opendomain Tasks