Ryan R. Curtin

Learn More
Deep neural networks (DNNs) are powerful nonlinear architectures that are known to be robust to random perturbations of the input. However, these models are vulnerable to adversarial perturbations—small input changes crafted explicitly to fool the model. In this paper, we ask whether a DNN can distinguish adversarial samples from their normal and noisy(More)
MLPACK is a new, state-of-the-art, scalable C++ machine learning library, which will be released in early December 2011. Its aim is to make large-scale machine learning possible for novice users by means of a simple, consistent API, while simultaneously exploiting C++ language features to provide maximum performance and maximum flexibility for expert users.(More)
The wide applicability of kernels makes the problem of max-kernel search ubiquitous and more general than the usual similarity search in metric spaces. We focus on solving this problem efficiently. We begin by characterizing the inherent hardness of the max-kernel search problem with a novel notion of directional concentration. Following that, we present a(More)
The problem of max-kernel search arises everywhere: given a query point pq , a set of reference objects Sr and some kernel K, find arg maxpr∈Sr K(pq , pr ). Max-kernel search is ubiquitous and appears in countless domains of science, thanks to the wide applicability of kernels. A few domains include image matching, information retrieval, bio-informatics,(More)
Dual-tree algorithms are a widely used class of branch-and-bound algorithms. Unfortunately, developing dual-tree algorithms for use with different trees and problems is often complex and burdensome. We introduce a four-part logical split: the tree, the traversal, the point-to-point base case, and the pruning rule. We provide a meta-algorithm which allows(More)
Numerous machine learning algorithms contain pairwise statistical problems at their core— that is, tasks that require computations over all pairs of input points if implemented naively. Often, tree structures are used to solve these problems efficiently. Dual-tree algorithms can efficiently solve or approximate many of these problems. Using cover trees,(More)
This paper is an effort to help prevent broiler chicken mortality caused by stressful conditions. We assume a relation between broiler chicken vocalizations and stress; therefore, microphones were used to monitor a flock of birds over the course of their lifetime (approximately 65 days). A noise removal method based on spectral oversubtraction was developed(More)
Nearest neighbor search is a nearly ubiquitous problem in computer science. When nearest neighbors are desired for a query set instead of a single query point, dual-tree algorithms often provide the fastest solution, especially in low-to-medium dimensions (i.e. up to a hundred or so), and can give exact results or absolute approximation guarantees, unlike(More)