The FLAIRS poster track is designed to promote discussion of emerging ideas and work in order to encourage and help guide researchers — especially new researchers — who are able to present a full poster in the conference poster session and receive that critical work-shaping feedback that helps guide good work into great work. Abstracts of those posters appear here, which we hope to see fully developed into future FLAIRS papers..

Navigating a career constitutes one of life’s most enduring challenges, particularly within a unique organization like the US Navy. While the Navy has numerous resources for guidance, accessing and identifying key information sources across the many existing platforms can be challenging for sailors (e.g., determining the appropriate program or point of contact, developing an accurate understanding of the process, and even recognizing the need for planning itself). Focusing on intermediate goals, evaluations, education, certifications, and training is quite demanding, even before considering their cumulative long-term implications. These are on top of generic personal issues, such as financial difficulties and homesickness when at sea for prolonged periods. We present the preliminary construction of a conversational intelligent agent designed to provide a user-friendly, adaptive environment that recognizes user input pertinent to these issues and provides guidance to appropriate resources within the Navy. User input from “counseling sessions” is linked, using advanced natural language processing techniques, to our framework of Navy training and education standards, promotion protocols, and organizational structure, producing feedback on resources and recommendations sensitive to user history and stated career goals. The proposed innovative technology monitors sailors’ career progress, proactively triggering sessions before major career milestones or when performance drops below Navy expectations, by using a mixed-initiative design. System-triggered sessions involve positive feedback and informative dialogues (using existing Navy career guidance protocols). The intelligent agent also offers counseling for personal problems, triggering targeted dialogues designed to gather more information, offer tailored suggestions, and provide referrals to appropriate resources or to a human counselor when in-depth counseling is warranted. This software, currently in alpha testing, has the potential to serve as a centralized information hub, engaging and encouraging sailors to take ownership of their career paths in the most efficient way possible, benefiting both individuals and the Navy as a whole.

In this paper, we aim to predict students’ learning perfor-mance by combining two-modality sensing variables, namely eye tracking that monitors learners’ eye movements and elec-troencephalography (EEG) that measures learners’ cerebral activity. Our long-term goal is to use both data to provide ap-propriate adaptive assistance for students to enhance their learning experience and optimize their performance. An ex-perimental study was conducted in order to collet gaze data and brainwave signals of fifteen students during an interac-tion with a virtual learning environment. Different classifica-tion algorithms were used to discriminate between two groups of learners: students who successfully resolve the problem-solving tasks and students who do not. Experimental results demonstrated that the K-Nearest Neighbor classifier achieved good accuracy when combining both eye movement and EEG features compared to using solely eye movement or EEG.

We consider learning problems of an intuitive and concise preference model, called lexicographic preference lists (LP-lists). Given a set of examples that are pair- wise ordinal preferences over a universe of objects built of attributes of discrete values, we want to learn (1) an optimal LP-list that decides the maximum number of these examples, or (2) a near-optimal LP-list that decides as many examples as it can. To this end, we introduce a dynamic programming based algorithm and a genetic algorithm for these two learning problems, respectively. Furthermore, we empirically demonstrate that the sub-optimal models computed by the genetic algorithm very well approximate the de facto optimal models computed by our dynamic programming based algorithm, and that the genetic algorithm outperforms the existing greedy heuristic with higher accuracy predicting new preferences.

Gifted students have a higher capabilities of understanding and learning. They are characterized by a high level of attention and a high performance in the classroom. Gifted children are defined in this paper as children who have a performance higher than the average group (59.64%). In order to predict gifted students from normal students, we conducted an experiment where 17 pupils have voluntarily participated in this study. We collected different types of data (gender, age, performance, initial average in math and EEG mental states) in a web platform to learn mathematics called NetMath. Participants were invited to respond to top-level exercises on the four basic operations in decimals. We trained different machine learning algorithms to predict gifted students. Our first results show that the decision tree could predict gifted students with an accuracy of 76.88%. Using J48 trees, we noticed also that two relevant features could determine gifted children: the relaxation extracted from EEG headset and the characteristic of strong student. A strong student is defined as a student who obtained a mean higher than the group’s mean in the first step evaluation in class.

We propose a concept map based approach to assessing freely generated student responses. The proposed approach is based on a novel automated tuple extraction system, DT-OpenIE, for automatically extracting concept maps from student responses. The DT-OpenIE system is significantly better in terms of concept map quality for assessment purposes than state-of-the-art open information extraction (IE) systems such as Ollie or Stanford as evidenced by our experimental results. The concept map based approach can significantly improve tracking student's mastery level in an automated tutoring environment such as DeepTutor where students interact with the automated tutor using natural language because the concept maps can be used not only to generate a holistic score assessing the accuracy of a student response but also enable diagnostic feedback.

Semantic similarity is a major automated approach to address many tasks such as essay grading, answer assessment, text summarization and information retrieval. Many semantic similarity methods rely on semantic representation such as Latent Semantic Analysis (LSA), an unsupervised method to infer a vectorial semantic representation of words or larger texts such as documents. Two ingredients in obtaining LSA vectorial representations are the corpus of texts from which the vectors are derived and the dimensionality of the resulting space. In this work, we investigate the effect of corpus size and vector dimensionality on assessing student generated content in advanced learning systems, namely, virtual internships. Automating the assessment of student generated content would greatly increase the scalability of virtual internships to millions of learners at reasonable costs. Prior work on automated assessment of notebook entries relied on classifiers trained on participant data. However, when new virtual internships are created for a new domain, for instance, no participant data is available a priori. Here, we report on our effort to develop a LSA-based assessment method without student data. Furthermore, we investigate the optimum corpus size and vector dimensionality for these LSA-based methods.

Humans achieve efficient learning by relying on prior knowledge about the structure of naturally occurring tasks. There has been considerable interest in designing reinforcement learning algorithms with similar properties. This includes several proposals to learn the learning algorithm itself, an idea also referred to as meta learning. One formal interpretation of this idea is in terms of a partially observable multi-task reinforcement learning problem in which information about the task is hidden from the agent. Although agents that solve partially observable environments can be trained from rewards alone, shaping an agent's memory with additional supervision has been shown to boost learning efficiency. It is thus natural to ask what kind of supervision, if any, facilitates meta-learning. Here we explore several choices and develop an architecture that separates learning of the belief about the unknown task from learning of the policy, and that can be used effectively with privileged information about the task during training. We show that this approach can be very effective at solving standard meta-RL environments, as well as a complex continuous control environment in which a simulated robot has to execute various movement sequences.

Model-free reinforcement learning based methods such as Proximal Policy Optimization, or Q-learning typically require thousands of interactions with the environment to approximate the optimum controller which may not always be feasible in robotics due to safety and time consumption. Model-based methods such as PILCO or BlackDrops, while data-efficient, provide solutions with limited robustness and complexity. To address this tradeoff, we introduce active uncertainty reduction-based virtual environments, which are formed through limited trials conducted in the original environment. We provide an efficient method for uncertainty management, which is used as a metric for self-improvement by identification of the points with maximum expected improvement through adaptive sampling. Capturing the uncertainty also allows for better mimicking of the reward responses of the original system. Our approach enables the use of complex policy structures and reward functions through a unique combination of model-based and model-free methods, while still retaining the data efficiency. We demonstrate the validity of our method on several classic reinforcement learning problems in OpenAI gym. We prove that our approach offers a better modeling capacity for complex system dynamics as compared to established methods.

Generative Adversarial Networks have shown remarkable success in learning a distribution that faithfully recovers a reference distribution in its entirety. However, in some cases, we may want to only learn some aspects (e.g., cluster or manifold structure), while modifying others (e.g., style, orientation or dimension). In this work, we propose an approach to learn generative models across such incomparable spaces, and demonstrate how to steer the learned distribution towards target properties. A key component of our model is the Gromov-Wasserstein distance, a notion of discrepancy that compares distributions relationally rather than absolutely. While this framework subsumes current generative models in identically reproducing distributions, its inherent flexibility allows application to tasks in manifold learning, relational learning and cross-domain learning.