Search For:

Displaying 1-7 out of 7 total
Interactive Machine Learning in Data Exploitation
Found in: Computing in Science & Engineering
By Reid Porter,James Theiler,Don Hush
Issue Date:September 2013
pp. 12-20
The goal of interactive machine learning is to help scientists and engineers exploit more specialized data from within their deployed environment in less time, with greater accuracy and fewer costs. A basic introduction to the main components is provided h...
Faster and Better: A Machine Learning Approach to Corner Detection
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Edward Rosten, Reid Porter, Tom Drummond
Issue Date:January 2010
pp. 105-119
The repeatability and efficiency of a corner detector determines how likely it is to be useful in a real-world application. The repeatability is important because the same scene viewed from different positions should yield features which correspond to the ...
Rotationally invariant sparse patch matching on GPU and FPGA
Found in: Parallel and Distributed Processing Symposium, International
By Zachary K. Baker, Reid Porter
Issue Date:April 2008
pp. 1-8
Vector and data-flow processors are particularly strong at dense, regular computation. Sparse, irregular data layouts cause problems because their unpredictable data access patterns prevent computational pipelines from filling effectively. A number of algo...
A Programmable, Maximal Throughput Architecture for Neighborhood Image Processing
Found in: Field-Programmable Custom Computing Machines, Annual IEEE Symposium on
By Reid Porter, Jan Frigo, Maya Gokhale, Christophe Wolinski, Francois Charot, Charles Wagner
Issue Date:April 2006
pp. 279-280
We propose a run-time re-configurable architecture for local neighborhood image processing. We discuss how the new architecture can offer improved flexibility to the developer. We show that for a satellite image feature extraction application, our architec...
Unsupervised Adaptation to Improve Fault Tolerance of Neural Network Classifiers
Found in: Evolvable Hardware, NASA/DoD Conference on
By Alex Nugent, Garret Kenyon, Reid Porter
Issue Date:June 2004
pp. 146
We investigate how to exploit the dynamics of unsupervised online learning rules for fault tolerance in neural network classifiers. We first design an adaptation mechanism that keeps neural network weights at a useful fixed point for classification problem...
Evolving Network Architectures With Custom Computers For Multi-Spectral Feature Identification
Found in: Evolvable Hardware, NASA/DoD Conference on
By Reid Porter, Maya Gokhale Neal Harvey, Simon Perkins, Cody Young
Issue Date:July 2001
pp. 0261
Abstract: This paper investigates the design of evolvable FPGA circuits where the design space is severely constrained to an interconnected network of meaningful high-level operators. The specific design domain is image processing, especially pattern recog...
An Applications Approach to Evolvable Hardware
Found in: Evolvable Hardware, NASA/DoD Conference on
By Reid Porter, Kevin McCabe, Neil Bergmann
Issue Date:July 1999
pp. 170
We discuss the use of Field Programmable Gate Arrays (FPGAs) as hardware accelerators in genetic algorithm (GA) applications. The research is particularly focused on image processing optimization problems where fitness evaluation is computationally demandi...