a general strongsystemstrong for learning and reasoning in symbolic.pdfVIP

A General System for Learning and Reasoning in Symbolic Domains 1 2 3 Claes Stranneg˚ard , Abdul Rahim Nizamani , and Ulf Persson 1 Department of Philosophy, Linguistics and Theory of Science, University of Gothenburg, Sweden and Department of Applied Information Technology, Chalmers University of Technology, Sweden claes.strannegard@gu.se 2 Department of Applied Information Technology, University of Gothenburg, Sweden abdulrahim.nizamani@gu.se 3 Department of Mathematical Sciences, Chalmers University of Technology, Sweden ulfp@chalmers.se Abstract. We present the system O that operates in arbitrary symbolic domains, including arithmetic, logic, and grammar. O can start from scratch and learn the general laws of a domain from examples. The main learning mechanism is a for- malization of Occam’s razor. Learning is facilitated by working within a cognitive model of bounded rationality. Computational complexity is thereby dramatically reduced, while preserving human-level performance. As illustration, we describe the learning process by which O learns elementary arithmetic. In the beginning, O knows nothing about the syntax or laws of arithmetic; by the end, it has con- structed a theory enabling it to solve previously unseen problems such as “what is 67 ∗ 8?” and “which number comes next in the sequence 8, 11, 14?”. Keywords: Domain-independent agent, Occam’s razor, bounded rationality. 1 Introduction The goal of artificial general intelligence (AGI) is to build systems with general in- telligence at the human level or beyond