We present the design and deployment of a physical computing platform developed for a crossdisciplinary introduction to biology and computer science. Using the accessible Arduino interface as its foundation, students instantiate increasingly nuanced physical interactions with the environment. Biological and computational ideas receive equal attention through three layered projects that span from circuit design through the co-evolution of predator-prey robot behaviors. The low-overhead platform presented here scales to support sophisticated projects at surprisingly modest time-and-money costs

For the past several years, we have been using robots in our introductory computer science course. Although this has been challenging for many reasons, it has also been very rewarding on a number of fronts, both for the students and for us. However, in order for this to occur, we had to adapt to what we perceived as “chaotic code.” In this paper we describe lessons learned by watching what the students do, where they have trouble, and what they enjoy. Further, we discuss what the implications of focusing on creativity has had on teaching and assessment.

A key challenge for policymakers in many developing countries is to decide which intervention or collection of interventions works best to improve learning outcomes in their schools. Our aim is to develop a causal model that explains student learning outcomes in terms of observable characteristics as well as conditions and processes difficult to observe directly. We start with a theoretical model based on the results of previous research, direct experience and experts’ knowledge in the field. This model is then refined through application of supervised learning methods to available data sets. Once calibrated with local data in a country, the model estimates the probability that a given intervention would affect learning outcomes.

There is a wealth of information on the Web about any number of topics. Many communities in developing regions are often interested in information relating to specific topics. For example, health workers are interested in specific medical information regarding epidemic diseases in their region while teachers and students are interested in educational information relating to their curriculum. This paper presents the design of Contextual Information Portals, searchable information portals that contain a vertical slice of the Web about arbitrary topics tailored to a specific context. Contextual portals are particularly useful for communities that lack Internet or Web access or in regions with very poor network connectivity. This paper outlines the design space for constructing contextual information portals and describes the key technical challenges involved. We have implemented a proof-of-concept of our ideas, and performed an initial evaluation on a variety of topics relating to epidemiology, agriculture, and education.

In many AI domains such as product configuration, a user should interactively specify a solution that must satisfy a set of constraints. In such scenarios, offline compilation of feasible solutions into a tractable representation is an important approach to delivering efficient backtrack-free user interaction online. In particular,binary decision diagrams (BDDs) have been successfully used as a compilation target for product and service configuration. In this paper we discuss how to extend BDD-based configuration to scenarios involving cost functions which express user preferences. We first show that an efficient, robust and easy to implement extension is possible if the cost function is additive, and feasible solutions are represented using multi-valued decision diagrams (MDDs). We also discuss the effect on MDD size if the cost function is non-additive or if it is encoded explicitly into MDD. We then discuss interactive configuration in the presence of multiple cost functions. We prove that even in its simplest form, multiple-cost configuration is NP-hard in the input MDD. However, for solving two-cost configuration we develop a pseudo-polynomial scheme and a fully polynomial approximation scheme. The applicability of our approach is demonstrated through experiments over real-world configuration models and product-catalogue datasets. Response times are generally within a fraction of a second even for very large instances.

Although AI and HCI explore computing and intelligent behavior and the fields have seen some cross-over, until recently there was not very much. This article outlines a history of the fields that identifies some of the forces that kept the fields at arm’s length. AI was generally marked by a very ambitious, long-term vision requiring expensive systems, although the term was rarely envisioned as being as long as it proved to be, whereas HCI focused more on innovation and improvement of widely-used hardware within a short time-scale. These differences led to different priorities, methods, and assessment approaches.  A consequence was competition for resources, with HCI flourishing in AI winters and moving more slowly when AI was in favor. The situation today is much more promising, in part because of platform convergence: AI can be exploited on widely-used systems.

This case study article describes the iterative design process of an adaptive, mixed-initiative calendaring tool with embedded artificial intelligence.  We establish the specific types of assistance in which the target user population expressed interest, and we highlight our findings regarding the scheduling practices and the reminding preferences of these users.  These findings motivated the redesign and enhancement of our intelligent system.  Lessons learned from the study—namely, highlighting the merits of usability toward widespread adoption and retention, and that simple problems that perhaps do not necessitate complex AI-based solutions should not go unattended merely due to their inherent simplicity—conclude the article, along with a discussion of the importance of the iterative design process for any user adaptive system.

Learning in real-time applications, e.g., online approximation of the inverse dynamics model for model-based robot control, requires fast online regression techniques. Inspired by local learning, we propose a method to speed up standard Gaussian Process regression (GPR) with local GP models (LGP). The training data is partitioned in local regions, for each an individual GP model is trained. The prediction for a query point is performed by weighted estimation using nearby local models. Unlike other GP approximations, such as mixtures of experts, we use a distance based measure for partitioning of the data and weighted prediction. The proposed method achieves online learning and prediction in real-time. Comparisons with other nonparametric regression methods show that LGP has higher accuracy than LWPR and close to the performance of standard GPR and nu-SVR.

Metric learning algorithms can provide useful distance functions for a variety of domains, and recent work has shown good accuracy for problems where the learner can access all distance constraints at once. However, in many real applications, constraints are only available incrementally, thus necessitating methods that can perform online updates to the learned metric. Existing online algorithms offer bounds on worst-case performance, but typically do not perform well in practice as compared to their offline counterparts. We present a new online metric learning algorithm that updates a learned Mahalanobis metric based on LogDet regularization and gradient descent. We prove theoretical worst-case performance bounds, and empirically compare the proposed method against existing online metric learning algorithms. To further boost the practicality of our approach, we develop an online locality-sensitive hashing scheme which leads to efficient updates for approximate similarity search data structures. We demonstrate our algorithm on multiple datasets and show that it outperforms relevant baselines.

We propose a novel information theoretic approach for semi-supervised learning of conditional random fields. Our approach defines a training objective that combines the conditional likelihood on labeled data and the mutual information on unlabeled data. Different from previous minimum conditional entropy semi-supervised discriminative learning methods, our approach can be naturally cast into the rate distortion theory framework in information theory. We analyze the tractability of the framework for structured prediction and present a convergent variational training algorithm to defy the combinatorial explosion of terms in the sum over label configurations. Our experimental results show that the rate distortion approach outperforms standard $l_2$ regularization and minimum conditional entropy regularization on both multi-class classification and sequence labeling problems.