Purely data driven approaches for machine learning present difficulties when data is scarce relative to the complexity of the model or when the model is forced to extrapolate. On the other hand, purely mechanistic approaches need to identify and specify all the interactions in the problem at hand (which may not be feasible) and still leave the issue of how to parameterize the system. In this paper, we present a hybrid approach using Gaussian processes and differential equations to combine data driven modelling with a physical model of the system. We show how different, physically-inspired, kernel functions can be developed through sensible, simple, mechanistic assumptions about the underlying system. The versatility of our approach is illustrated with three case studies from motion capture, computational biology and geostatistics.

Given a point cloud, we consider inferring kinematic models of 3D articulated objects such as boxes for the purpose of manipulating them. While previous work has shown how to extract a planar kinematic model (often represented as a linear chain), such planar models do not apply to 3D objects that are composed of segments often linked to the other segments in cyclic configurations. We present an approach for building a model that captures the relation between the input point cloud features and the object segment as well as the relation between the neighboring object segments. We use a conditional random field that allows us to model the dependencies between different segments of the object. We test our approach on inferring the kinematic structure from partial and noisy point cloud data for a wide variety of boxes including cake boxes, pizza boxes, and cardboard cartons of several sizes. The inferred structure enables our robot to successfully close these boxes by manipulating the flaps.

In the current study we examine an application of the machine learning methods to model the retention constants in the thin layer chromatography (TLC). This problem can be described with hundreds or even thousands of descriptors relevant to various molecular properties, most of them redundant and not relevant for the retention constant prediction. Hence we employed feature selection to significantly reduce the number of attributes. Additionally we have tested application of the bagging procedure to the feature selection. The random forest regression models were built using selected variables. The resulting models have better correlation with the experimental data than the reference models obtained with linear regression. The cross-validation confirms robustness of the models.

The Baire metric induces an ultrametric on a dataset and is of linear computational complexity, contrasted with the standard quadratic time agglomerative hierarchical clustering algorithm. In this work we evaluate empirically this new approach to hierarchical clustering. We compare hierarchical clustering based on the Baire metric with (i) agglomerative hierarchical clustering, in terms of algorithm properties; (ii) generalized ultrametrics, in terms of definition; and (iii) fast clustering through k-means partititioning, in terms of quality of results. For the latter, we carry out an in depth astronomical study. We apply the Baire distance to spectrometric and photometric redshifts from the Sloan Digital Sky Survey using, in this work, about half a million astronomical objects. We want to know how well the (more costly to determine) spectrometric redshifts can predict the (more easily obtained) photometric redshifts, i.e. we seek to regress the spectrometric on the photometric redshifts, and we use clusterwise regression for this.

Data mining has primarily focused on statistical properties of data alone and not necessarily on what could be done with the patterns. While there has been some work on measuring usefulness of patterns in decision making but not on using such measures for driving the mining process. We introduce a framework to mine clusters that support decision making. We use an extrinsic measure that evaluates patterns based on their utility in decision making. We show empirical validationof our approach on several test domains.

Community mining is applied in order to identify groups of users which share, e.g., common interests or expertise. This paper presents an approach for mining descriptive patterns in order to characterize communities in terms of their distinctive features: For an efficient discovery approach, we introduce optimistic estimates for obtaining an upper bound for the community quality. We present an evaluation using data from the real-world social bookmarking system BibSonomy.

Sequential decision tasks present many opportunities for the study of transfer learning. A principal one among them is the existence of multiple domains that share the same underlying causal structure for actions. We describe an approach that exploits this shared causal structure to discover a hierarchical task structure in a source domain, which in turn speeds up learning of task execution knowledge in a new target domain. Our approach is theoretically justified and compares favorably to manually designed task hierarchies in learning efficiency in the target domain. We demonstrate that causally motivated task hierarchies transfer more robustly than other kinds of detailed knowledge that depend on the idiosyncrasies of the source domain and are hence less transferable.

Sustainable building design is a complex social and technical process in which a broad range of stakeholders must construct and clearly communicate high quality design spaces. This paper summarizes recent assessments of current practice that illustrate how far industry today is from achieving this quality and clarity. Efforts to develop a platform of tools to address these limitations are discussed. PIP helps people communicate, share, and understand collaborative design processes; MACDADI helps project teams identify and manage rationale and consensus on decisions; Design Scenarios helps them generate requirements-driven alternative spaces, BIM, model-based analysis, and PIDO which helps to systematically assess these alternatives for their energy, daylight, structural, and cost impacts; and iRooms and the web, which help to communicate all of this information to engage designers, stakeholders, and decision makers in fast, multidisciplinary design and analysis processes. This new platform considerably improves the quality and clarity of AEC design spaces. However additional work would enable significant additional improvement. The paper concludes with a proposal for how AI might further improve the performance of this platform.

We consider the problem of assessing the sustainability of alternative designs (e.g., for an urban environment) that are assembled from multiple components (e.g., water supply, transportation system, shopping centers, commercial spaces, parks). We model the sustainability of a design in terms of a set of sustainability attributes. Given the (qualitative) preferences and tradeoffs of decision makers over the sustainability attributes, we formulate the problem of identifying sustainable designs as the problem of finding the most preferred designs with respect to those preferences. We show how techniques for representing and reasoning with qualitative preferences can be used to identify the most preferred designs based on the decision maker’s stated preferences and tradeoffs.

Although researchers often comment on the rising popularity of nature-inspired meta-heuristics (NIM), there has been a paucity of data to directly support the claim that NIM are growing in prominence compared to other optimization techniques. This study presents evidence that the use of NIM is not only growing, but indeed appears to have surpassed mathematical optimization techniques (MOT) in several important metrics related to academic research activity (publication frequency) and commercial activity (patenting frequency). Motivated by these findings, this article discusses some of the possible origins of this growing popularity. I review different explanations for NIM popularity and discuss why some of these arguments remain unsatisfying. I argue that a compelling and comprehensive explanation should directly account for the manner in which most NIM success has actually been achieved, e.g. through hybridization and customization to different problem environments. By taking a problem lifecycle perspective, this paper offers a fresh look at the hypothesis that nature-inspired meta-heuristics derive much of their utility from being flexible. I discuss global trends within the business environments where optimization algorithms are applied and I speculate that highly flexible algorithm frameworks could become increasingly popular within our diverse and rapidly changing world.