In practice, training language models for individual authors is often expensive because of limited data resources. In such cases, Neural Network Language Models (NNLMs), generally outperform the traditional non-parametric N-gram models. Here we investigate the performance of a feed-forward NNLM on an authorship attribution problem, with moderate author set size and relatively limited data. We also consider how the text topics impact performance. Compared with a well-constructed N-gram baseline method with Kneser-Ney smoothing, the proposed method achieves nearly 2.5% reduction in perplexity and increases author classification accuracy by 3.43% on average, given as few as 5 test sentences. The performance is very competitive with the state of the art in terms of accuracy and demand on test data.

Advances in natural language processing (NLP) and educational technology, as well as the availability of unprecedented amounts of educationally-relevant text and speech data, have led to an increasing interest in using NLP to address the needs of teachers and students. Educational applications differ in many ways, however, from the types of applications for which NLP systems are typically developed. This paper will organize and give an overview of research in this area, focusing on opportunities as well as challenges.

We developed a course in which students train an instance of Watson and develop an application that interacts with the trained instance. Additionally, students learn technical in-formation about the Jeopardy! version of Watson and they discuss a future infused with cognitive assistants. In this poster, we justify this course, characterize major assessment items and provide advice on choosing a domain.

This paper discusses the design of an introductory computer science course for high school students using declarative programming. Though not often taught at the K-12 level, declarative programming is a viable paradigm for teaching computer science due to its importance in artificial intelligence and in helping student explore and understand problem spaces. This paper describes the authors' implementation of a declarative programming course for high school students during a 4-week summer session.

While many computer science programs offer courses on research methods, such classes typically tend to be aimed at graduate students. In this paper, we propose a novel means for introducing undergraduate students to research experiences in computer science — via an introductory Artificial Intelligence (A.I.) course. Students explore the content areas typically covered in an upper-level A.I. course (heuristic search, constraint satisfaction, game-playing etc.), while also learning about the mechanics of how empirical research is conducted in this field.

The field of AI has changed significantly in the past couple of years and will likely continue to do so. Driven by a desire to expose our students to relevant and modern materials, we conducted two surveys, one of AI instructors and one of AI practitioners. The surveys were aimed at gathering infor-mation about the current state of the art of introducing AI as well as gathering input from practitioners in the field on techniques used in practice. In this paper, we present and briefly discuss the responses to those two surveys.

Teaching artificial intelligence is effective if the experience is a visual and interactive one, with educational materials that utilize combinations of various content types such as text, math, and code into an integrated experience. Unfortunately, easy-to-use tools for creating such pedagogical resources are not available to the educators, resulting in most courses being taught using a disconnected set of static materials, which is not only ineffective for learning AI, but further, requires repeated and redundant effort for the instructor. In this paper, we introduce Moro, a software tool for easily creating and presenting AI-friendly teaching materials. Moro notebooks integrate content of different types (text, math, code, images), allow real-time interactions via modifiable and executable code blocks, and are viewable in browsers both as long-form pages and as presentations. Creating notebooks is easy and intuitive; the creation tool is also in-browser, is WYSIWYG for quick iterations of editing, and supports a variety of shortcuts and customizations for efficiency. We present three deployed case studies of Moro that widely differ from each other, demonstrating its utility in a variety of scenarios such as in-class teaching and conference tutorials.

In Fall 2014 we offered an online course on Knowledge-Based Artificial Intelligence (KBAI) to about 200 students as part of the Georgia Tech Online MS in CS program. By now we have offered the course to more than 1000 students. We describe the design, development and delivery of the online KBAI class in Fall 2014.

We have designed an open and modular course for data science and big data analytics using a workflow paradigm that allows students to easily experience big data through a sophisticated yet easy to use instrument that is an intelligent workflow system. A key aspect of this work is the use of semantic workflows to capture and reuse end-to-end analytic methods that experts would use to analyze big data, and the use of an intelligent workflow system to elaborate the workflow and manage its execution and resulting datasets. Through the exposure of big data analytics in a workflow framework, students will be able to get first-hand experiences with a breadth of big data topics, including multi-step data analytic and statistical methods, software reuse and composition, parallel distributed programming, high-end computing. In addition, students learn about a range of topics in AI, including semantic representations and ontologies, machine learning, natural language processing, and image analysis.

Effective training of deep neural networks suffers from two main issues. The first is that the parameter space of these models exhibit pathological curvature. Recent methods address this problem by using adaptive preconditioning for Stochastic Gradient Descent (SGD). These methods improve convergence by adapting to the local geometry of parameter space. A second issue is overfitting, which is typically addressed by early stopping. However, recent work has demonstrated that Bayesian model averaging mitigates this problem. The posterior can be sampled by using Stochastic Gradient Langevin Dynamics (SGLD). However, the rapidly changing curvature renders default SGLD methods inefficient. Here, we propose combining adaptive preconditioners with SGLD. In support of this idea, we give theoretical properties on asymptotic convergence and predictive risk. We also provide empirical results for Logistic Regression, Feedforward Neural Nets, and Convolutional Neural Nets, demonstrating that our preconditioned SGLD method gives state-of-the-art performance on these models.