We investigate a population of binary mistake sequences that result from learning with parametric models of different order. We obtain estimates of their error, algorithmic complexity and divergence from a purely random Bernoulli sequence. We study the relationship of these variables to the learner's information density parameter which is defined as the ratio between the lengths of the compressed to uncompressed files that contain the learner's decision rule. The results indicate that good learners have a low information density$\rho$ while bad learners have a high $\rho$. Bad learners generate mistake sequences that are atypically complex or diverge stochastically from a purely random Bernoulli sequence. Good learners generate typically complex sequences with low divergence from Bernoulli sequences and they include mistake sequences generated by the Bayes optimal predictor. Based on the static algorithmic interference model of \cite{Ratsaby_entropy} the learner here acts as a static structure which "scatters" the bits of an input sequence (to be predicted) in proportion to its information density $\rho$ thereby deforming its randomness characteristics.

This paper discusses the benefits of describing the world as information, especially in the study of the evolution of life and cognition. Traditional studies encounter problems because it is difficult to describe life and cognition in terms of matter and energy, since their laws are valid only at the physical scale. However, if matter and energy, as well as life and cognition, are described in terms of information, evolution can be described consistently as information becoming more complex. The paper presents eight tentative laws of information, valid at multiple scales, which are generalizations of Darwinian, cybernetic, thermodynamic, psychological, philosophical, and complexity principles. These are further used to discuss the notions of life, cognition and their evolution.

This paper is mainly concerned with the question of how to decompose multiclass classification problems into binary subproblems. We extend known Jensen-Shannon bounds on the Bayes risk of binary problems to hierarchical multiclass problems and use these bounds to develop a heuristic procedure for constructing hierarchical multiclass decomposition for multinomials. We test our method and compare it to the well known "all-pairs" decomposition. Our tests are performed using a new authorship determination benchmark test of machine learning authors. The new method consistently outperforms the all-pairs decomposition when the number of classes is small and breaks even on larger multiclass problems. Using both methods, the classification accuracy we achieve, using an SVM over a feature set consisting of both high frequency single tokens and high frequency token-pairs, appears to be exceptionally high compared to known results in authorship determination.

Report on the Third Conference on Artificial General Intelligence

The 23rd International Florida Artificial Intelligence Research Society Conference (FLAIRS-23) was held May 19-21, 2010 at The Shores Resort & Spa in Daytona Beach Shores, Florida, USA. The conference featured an exciting lineup of invited speakers, a general conference track on artificial intelligence research, and numerous special tracks. The conference chair was David Wilson from the University of North Carolina at Charlotte. The special tracks coordinator was Philip McCarthy from the University of Memphis.

Information extraction (IE) can identify a set of relations from free text to support question answering (QA). Until recently, IE systems were domain-specific and needed a combination of manual engineering and supervised learning to adapt to each target domain. A new paradigm, Open IE operates on large text corpora without any manual tagging of relations, and indeed without any pre-specified relations. We explore the steps needed to adapt Open IE to a domain-specific ontology and demonstrate our approach of mapping domain-independent tuples to an ontology using domains from DARPA's Machine Reading Project.

This article gives a detailed description of True Knowledge: a commercial, open-domain question answering platform. The system combines a large and growing structured knowledge base of common sense, factual and lexical knowledge; a natural language translation system that turns user questions into internal language-independent queries and an inference system that can answer those queries using both directly represented and inferred knowledge. The system is live and answers millions of questions per month asked by internet users.

The Association for the Advancement of Artificial Intelligence, in cooperation with Stanford University's Department of Computer Science, is pleased to present the 2010 Spring Symposium Series, to be held Monday through Wednesday, March 22–24, 2010 at Stanford University. The titles of the seven symposia are Artificial Intelligence for Development; Cognitive Shape Processing; Educational Robotics and Beyond: Design and Evaluation; Embedded Reasoning: Intelligence in Embedded Systems Intelligent Information Privacy Management; It's All in the Timing: Representing and Reasoning about Time in Interactive Behavior; and Linked Data Meets Artificial Intelligence.

In the winter, 2004 issue of AI Magazine, we reported Vulcan Inc.'s first step toward creating a question-answering system called "Digital Aristotle." The goal of that first step was to assess the state of the art in applied Knowledge Representation and Reasoning (KRR) by asking AI experts to represent 70 pages from the advanced placement (AP) chemistry syllabus and to deliver knowledge-based systems capable of answering questions from that syllabus. This paper reports the next step toward realizing a Digital Aristotle: we present the design and evaluation results for a system called AURA, which enables domain experts in physics, chemistry, and biology to author a knowledge base and that then allows a different set of users to ask novel questions against that knowledge base. These results represent a substantial advance over what we reported in 2004, both in the breadth of covered subjects and in the provision of sophisticated technologies in knowledge representation and reasoning, natural language processing, and question answering to domain experts and novice users.

This special issue issue of AI Magazine presents six articles on some of the most interesting question answering systems in development today. Included are articles on Project, the Semantic Research, Watson, True Knowledge, and TextRunner (University of Washington's clever use of statistical NL techniques to answer questions across the open web).