A common approach to interactive narrative involves imbuing the computer with all of the potential story pre-authored story experiences (e.g. as beats, plot points, planning operators, etc.). This has resulted in an accepted paradigm where stories are not created by or with the user; rather, the user is given piecemeal access to the story from the gatekeeper of story knowledge: the computer (e.g. as an AI drama manager). This article describes a formal process that provides for the equal co-creation of story-rich experiences, where neither the user nor computer is in a privileged position in an interactive narrative. It describes a new formal approach that acts as a first step for the real-time co-creation of narrative in games that rely on the negotiated shared mental model between a human actor and an AI improv agent.

In this paper, we survey techniques used in intelligent tutoring systems (ITSs) to model student knowledge. The three techniques that we review in detail are knowledge tracing, performance factor analysis, and matrix factorization. We also briefly cover other techniques that have been used. This review is meant to be a repository of knowledge for those who want to integrate these techniques into serious games. It is also meant to increase awareness and interest as to the techniques available that can be integrated into serious games.

Imagine that a budding composer suffers from writer's block partway through devising a melody. A system called FreshJam is demonstrated, which offers a solution to this problem in the form of an interactive composition assistant; an algorithm that analyzes the notes composed so far, makes a comparison with an indexed corpus of existing music, and suggests a possible next note by choosing randomly among continuations of matched melody fragments. We provide a demonstration of FreshJam as an aid in stylistic composition, and of its potential to be more iterative than existing composition assistants such as PG Music's Band in a Box or Microsoft's Songsmith.

Mirror descent with an entropic regularizer is known to achieve shifting regret bounds that are logarithmic in the dimension. This is done using either a carefully designed projection or by a weight sharing technique. Via a novel unified analysis, we show that these two approaches deliver essentially equivalent bounds on a notion of regret generalizing shifting, adaptive, discounted, and other related regrets. Our analysis also captures and extends the generalized weight sharing technique of Bousquet and Warmuth, and can be refined in several ways, including improvements for small losses and adaptive tuning of parameters.

In E-learning, there is still the problem of knowing how to ensure an individualized and continuous learner's follow-up during learning process, indeed among the numerous tools proposed, very few systems concentrate on a real time learner's follow-up. Our work in this field develops the design and implementation of a Multi-Agents System Based on Dynamic Case Based Reasoning which can initiate learning and provide an individualized follow-up of learner. When interacting with the platform, every learner leaves his/her traces in the machine. These traces are stored in a basis under the form of scenarios which enrich collective past experience. The system monitors, compares and analyses these traces to keep a constant intelligent watch and therefore detect difficulties hindering progress and/or avoid possible dropping out. The system can support any learning subject. The success of a case-based reasoning system depends critically on the performance of the retrieval step used and, more specifically, on similarity measure used to retrieve scenarios that are similar to the course of the learner (traces in progress). We propose a complementary similarity measure, named Inverse Longest Common Sub-Sequence (ILCSS). To help and guide the learner, the system is equipped with combined virtual and human tutors.

In Natural Language Processing (NLP) tasks, data often has the following two properties: First, data can be chopped into multi-views which has been successfully used for dimension reduction purposes. For example, in topic classification, every paper can be chopped into the title, the main text and the references. However, it is common that some of the views are less noisier than other views for supervised learning problems. Second, unlabeled data are easy to obtain while labeled data are relatively rare. For example, articles occurred on New York Times in recent 10 years are easy to grab but having them classified as 'Politics', 'Finance' or 'Sports' need human labor. Hence less noisy features are preferred before running supervised learning methods. In this paper we propose an unsupervised algorithm which optimally weights features from different views when these views are generated from a low dimensional hidden state, which occurs in widely used models like Mixture Gaussian Model, Hidden Markov Model (HMM) and Latent Dirichlet Allocation (LDA).

We develop a model of issue-specific voting behavior. This model can be used to explore lawmakers' personal voting patterns of voting by issue area, providing an exploratory window into how the language of the law is correlated with political support. We derive approximate posterior inference algorithms based on variational methods. Across 12 years of legislative data, we demonstrate both improvement in heldout prediction performance and the model's utility in interpreting an inherently multi-dimensional space.

There is an increasing body of evidence suggesting that exact nearest neighbour search in high-dimensional spaces is affected by the curse of dimensionality at a fundamental level. Does it necessarily mean that the same is true for k nearest neighbours based learning algorithms such as the k-NN classifier? We analyse this question at a number of levels and show that the answer is different at each of them. As our first main observation, we show the consistency of a k approximate nearest neighbour classifier. However, the performance of the classifier in very high dimensions is provably unstable. As our second main observation, we point out that the existing model for statistical learning is oblivious of dimension of the domain and so every learning problem admits a universally consistent deterministic reduction to the one-dimensional case by means of a Borel isomorphism.

A society's single emergent, increasing intelligence arises partly from the thermodynamic advantages of networking the innate intelligence of different individuals, and partly from the accumulation of solved problems. Economic growth is proportional to the square of the network entropy of a society's population times the network entropy of the number of the society's solved problems.

We present a system that enables rapid model experimentation for tera-scale machine learning with trillions of non-zero features, billions of training examples, and millions of parameters. Our contribution to the literature is a new method (SA L-BFGS) for changing batch L-BFGS to perform in near real-time by using statistical tools to balance the contributions of previous weights, old training examples, and new training examples to achieve fast convergence with few iterations. The result is, to our knowledge, the most scalable and flexible linear learning system reported in the literature, beating standard practice with the current best system (Vowpal Wabbit and AllReduce). Using the KDD Cup 2012 data set from Tencent, Inc. we provide experimental results to verify the performance of this method.