APL Home
APL-UW Home

Jobs
About
Campus Map
Contact
Privacy
Intranet

Thomas Powers

Research Assistant & Research Assistant

Email

tcpowers@apl.washington.edu

Publications

2000-present and while at APL-UW

Building recurrent networks by unfolding iterative thresholding for equential sparse recovery

Wisdom, S., T. Powers, J. Pitton, and L. Atlas, "Building recurrent networks by unfolding iterative thresholding for equential sparse recovery," Proc., IEEE International Conference on Acoustics, Speech and Signal Processing, 5-9 March, New Orleans, LA, 4346-4350, doi:10.1109/ICASSP.2017.7952977 (IEEE, 2017).

More Info

19 Jun 2017

Historically, sparse methods and neural networks, particularly modern deep learning methods, have been relatively disparate areas. Sparse methods are typically used for signal enhancement, compression, and recovery, usually in an unsupervised framework, while neural networks commonly rely on a supervised training set. In this paper, we use the specific problem of sequential sparse recovery, which models a sequence of observations over time using a sequence of sparse coefficients, to show how algorithms for sparse modeling can be combined with supervised deep learning to improve sparse recovery. Specifically, we show that the iterative soft-thresholding algorithm (ISTA) for sequential sparse recovery corresponds to a stacked recurrent neural network (RNN) under specific architecture and parameter constraints. Then we demonstrate the benefit of training this RNN with backpropagation using supervised data for the task of column-wise compressive sensing of images. This training corresponds to adaptation of the original iterative thresholding algorithm and its parameters. Thus, we show by example that sparse modeling can provide a rich source of principled and structured deep network architectures that can be trained to improve performance on specific tasks.

Constrained robust submodular sensor selection with applications to multistatic sonar arrays

Powers, T., J. Bilmes, D.W. Krout, and L. Atlas, "Constrained robust submodular sensor selection with applications to multistatic sonar arrays," Proc., FUSION — 19th International Conference on Information Fusion, 5-8 July, 2179-2185 (IEEE, 2016).

More Info

4 Aug 2016

We develop a framework to select a subset of sensors from a field in which the sensors have an ingrained independence structure. Given an arbitrary independence pattern, we construct a graph that denotes pairwise independence between sensors, which means those sensors may operate simultaneously. The set of all fully-connected subgraphs (cliques) of this independence graph forms the independent sets of a matroid over which we maximize the minimum of a set of submodular objective functions. We propose a novel algorithm called MatSat that exploits submodularity and, as a result, returns a near-optimal solution with approximation guarantees that are within a small factor of the average-case scenario. We apply this framework to ping sequence optimization for active multistatic sonar arrays by maximizing sensor coverage and derive lower bounds for minimum probability of detection for a fractional number of targets. In these ping sequence optimization simulations, MatSat exceeds the fractional lower bounds and reaches near-optimal performance.

Acoustics Air-Sea Interaction & Remote Sensing Center for Environmental & Information Systems Center for Industrial & Medical Ultrasound Electronic & Photonic Systems Ocean Engineering Ocean Physics Polar Science Center
Close

 

Close