Conceptually founded on the "patternist" systems theory of intelligence outlined in (Goertzel 2006), OCP combines Defining Forgetting In ordinary human discourse, the multiple AI paradigms such as uncertain logic, computational word "forget" has multiple shades of meaning. It can refer linguistics, evolutionary program learning and connectionist to the irreversible elimination of a certain knowledge item attention allocation in a unified architecture. Cognitive from memory; or it can mean something milder, as in cases processes embodying these different paradigms interoperate where someone "forgets" something, but then remembers it together on a common neural-symbolic knowledge shortly after. In the latter case, "forgetting" means that the store called the Atomspace. The interaction of these processes knowledge item has been stored in some portion of memory is designed to encourage the self-organizing emergence from which access is slow and uncertain.

Autonomous robots demand complex behavior to deal with unstructured environments. To meet these expectations, a robot needs to address a suite of problems associated with long term knowledge acquisition, representation, and execution in the presence of partial information. In this paper, we address these issues by the acquisition of broad, domain general skills using an intrinsically motivated reward function. We show how these skills can be represented compactly and used hierarchically to obtain complex manipulation skills. We further present a Bayesian model using the learned skills to model objects in the world, in terms of the actions they afford. We argue that our knowledge representation allows a robot to both predict the dynamics of objects in the world as well as recognize them.

We propose an intelligent tutoring system that constructs a curriculum of hints and problems in order to teach a student skills with a rich dependency structure. We provide a template for building a multi-layered Dynamic Bayes Net to model this problem and describe how to learn the parameters of the model from data. Planning with the DBN then produces a teaching policy for the given domain. We test this end-to-end curriculum design system in two human-subject studies in the areas of finite field arithmetic and artificial language and show this method performs on par with hand-tuned expert policies.

We introduce a Java graphical gaming framework that enables students in an introductory artificial intelligence (AI) course to immediately apply and visualize the topics from class. We have used this framework in teaching a mixed undergraduate/graduate AI course for six years. We believe that the use of games motivates students. The graphical nature of each game enables students to quickly see how well their algorithm works. Because the topics in an introductory AI course vary widely, students apply their algorithms to multiple game environments. A final challenging environment enables them to tie together the concepts for the entire semester.

The undergraduate computer science curriculum is generally focused on skills and tools;  most students are not exposed to much  research in the field, and do not learn how to navigate the research literature.  We describe how science fiction reviews were used as a gateway to research reviews.  Students learn a little about current or recent research on a topic that stirs their imagination, and learn how to search for, read critically, and compare technical papers on a topic related their chosen science fiction book, movie, or TV show.

Integrating games into the computer science curriculum has been gaining acceptance in recent years, particularly when used to improve student engagement in introductory courses. This paper argues that games can also be useful in upper level courses, such as general artificial intelligence and machine learning. We provide a case study of using a Mario game in a machine learning class to provide one successful data point where both content-specific and general learning outcomes were successfully achieved.

A key problem in statistical modeling is model selection, how to choose a model at an appropriate level of complexity. This problem appears in many settings, most prominently in choosing the number ofclusters in mixture models or the number of factors in factor analysis. In this tutorial we describe Bayesian nonparametric methods, a class of methods that side-steps this issue by allowing the data to determine the complexity of the model. This tutorial is a high-level introduction to Bayesian nonparametric methods and contains several examples of their application.

Computational social choice is an expanding field that merges classical topics like economics and voting theory with more modern topics like artificial intelligence, multiagent systems, and computational complexity. This book provides a concise introduction to the main research lines in this field, covering aspects such as preference modelling, uncertainty reasoning, social choice, stable matching, and computational aspects of preference aggregation and manipulation. The book is centered around the notion of preference reasoning, both in the single-agent and the multi-agent setting. It presents the main approaches to modeling and reasoning with preferences, with particular attention to two popular and powerful formalisms, soft constraints and CP-nets. The authors consider preference elicitation and various forms of uncertainty in soft constraints.

In an introductory engineering course with an annual enrollment of over 1000 students, a professor has little option but to rely on multiple choice exams for midterms and finals. Furthermore, the teaching assistants are too overloaded to give detailed feedback on submitted homework assignments. We introduce Mechanix, a computer-assisted tutoring system for engineering students. Mechanix uses recognition of freehand sketches to provide instant, detailed, and formative feedback as the student progresses through each homework assignment, quiz, or exam. Free sketch recognition techniques allow students to solve free-body diagram and static truss problems as if they were using a pen and paper. The same recognition algorithms enable professors to add new unique problems simply by sketching out the correct answer. Mechanix is able to ease the burden of grading so that instructors can assign more free response questions, which provide a better measure of student progress than multiple choice questions do.

Designing dialog policies for voice-enabled interfaces is a tailoring job that is most often left to natural language processing experts. This job is generally redone for every new dialog task because cross-domain transfer is not possible. For this reason, machine learning methods for dialog policy optimization have been investigated during the last 15 years. Especially, reinforcement learning (RL) is now part of the state of the art in this domain. Standard RL methods require to test more or less random changes in the policy on users to assess them as improvements or degradations. This is called on policy learning. Nevertheless, it can result in system behaviors that are not acceptable by users. Learning algorithms should ideally infer an optimal strategy by observing interactions generated by a non-optimal but acceptable strategy, that is learning off-policy. In this contribution, a sample-efficient, online and off-policy reinforcement learning algorithm is proposed to learn an optimal policy from few hundreds of dialogues generated with a very simple handcrafted policy.