Structure Discovery in Nonparametric Regression through Compositional Kernel Search

Despite its importance, choosing the structural form of the kernel in nonparametric regression remains a black art. We define a space of kernel structures which are built compositionally by adding and multiplying a small number of base kernels. We present a method for searching over this space of structures which mirrors the scientific discovery process. The learned structures can often decompose functions into interpretable components and enable long-range extrapolation on time-series datasets. Our structure search method outperforms many widely used kernels and kernel combination methods on a variety of prediction tasks.

Independence is elusive: set size effects on encoding precision in visual search.

Looking for a target in a visual scene becomes more difficult as the number of stimuli increases. In a signal detection theory view, this is due to the cumulative effect of noise in the encoding of the distractors, and potentially on top of that, to an increase of the noise (i.e., a decrease of precision) per stimulus with set size, reflecting divided attention. It has long been argued that human visual search behavior can be accounted for by the first factor alone. While such an account seems to be adequate for search tasks in which all distractors have the same, known feature value (i.e., are maximally predictable), we recently found a clear effect of set size on encoding precision when distractors are drawn from a uniform distribution (i.e., when they are maximally unpredictable). Here we interpolate between these two extreme cases to examine which of both conclusions holds more generally as distractor statistics are varied. In one experiment, we vary the level of distractor heterogeneity; in another we dissociate distractor homogeneity from predictability. In all conditions in both experiments, we found a strong decrease of precision with increasing set size, suggesting that precision being independent of set size is the exception rather than the rule.

Fabrication and electrical integration of robust carbon nanotube micropillars by self-directed elastocapillary densification

Vertically aligned carbon nanotube (CNT) 'forest' microstructures fabricated by chemical vapor deposition (CVD) using patterned catalyst films typically have a low CNT density per unit area. As a result, CNT forests have poor bulk properties and are too fragile for integration with microfabrication processing. We introduce a new self-directed capillary densification method where a liquid is controllably condensed onto and evaporated from the CNT forests. Compared to prior approaches, where the substrate with CNTs is immersed in a liquid, our condensation approach gives significantly more uniform structures and enables precise control of the CNT packing density. We present a set of design rules and parametric studies of CNT micropillar densification by self-directed capillary action, and show that self-directed capillary densification enhances Young's modulus and electrical conductivity of CNT micropillars by more than three orders of magnitude. Owing to the outstanding properties of CNTs, this scalable process will be useful for the integration of CNTs as a functional material in microfabricated devices for mechanical, electrical, thermal and biomedical applications. © 2011 IOP Publishing Ltd.

Europium-directed self-assembly of a luminescent supramolecular gel from a tripodal terpyridine-based ligand.

Eu(III), the last piece in the puzzle: Europium-induced self-assembly of ligands having a C(3)-symmetrical benzene-1,3,5-tricarboxamide core results in the formation of luminescent gels. Supramolecular polymers are formed through hydrogen bonding between the ligands. The polymers are then brought together into the gel assembly through the coordination of terpyridine ends by Eu(III) ions (blue dashed arrow: distance between two ligands in the strand direction).

A high-performance Cantonese keyword search system

We present a system for keyword search on Cantonese conversational telephony audio, collected for the IARPA Babel program, that achieves good performance by combining postings lists produced by diverse speech recognition systems from three different research groups. We describe the keyword search task, the data on which the work was done, four different speech recognition systems, and our approach to system combination for keyword search. We show that the combination of four systems outperforms the best single system by 7%, achieving an actual term-weighted value of 0.517. © 2013 IEEE.

Light-directed writing of chemically tunable narrow-band holographic sensors

This tunable holographic sensor offers interrogation and a reporting transducer as well as an analyte-responsive hydrogel, rendering it label-free and reusable. A single 6 ns laser pulse is used to fabricate holographic sensors consisting of silver nanoparticles arranged periodically within a polymer film. The tunability of the sensor is demonstrated through pH sensing of artificial urine and validated through computational modeling. © 2014 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

Predictive entropy search for efficient global optimization of black-box functions

We propose a novel information-theoretic approach for Bayesian optimization called Predictive Entropy Search (PES). At each iteration, PES selects the next evaluation point that maximizes the expected information gained with respect to the global maximum. PES codifies this intractable acquisition function in terms of the expected reduction in the differential entropy of the predictive distribution. This reformulation allows PES to obtain approximations that are both more accurate and efficient than other alternatives such as Entropy Search (ES). Furthermore, PES can easily perform a fully Bayesian treatment of the model hyperparameters while ES cannot. We evaluate PES in both synthetic and real-world applications, including optimization problems in machine learning, finance, biotechnology, and robotics. We show that the increased accuracy of PES leads to significant gains in optimization performance.