JAMES E STECK

Prof. JAMES E STECK

orcid

Research Focus & Metrics

Academic Career Length

43Years (1984-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 October 2000 in Information Sciences
Verified
Journal Article
Closed access
EBElizabeth Behrman
Elizabeth Behrman
LNL.R. Nash
L.R. Nash
JAMES E STECKJAMES E STECK
JAMES E STECK
VCV.G. Chandrashekar
V.G. Chandrashekar
SSS.R. Skinner
S.R. Skinner

1 August 2021 in Expert Systems with Applications
Verified
Journal Article
Closed access
SBSima E. Borujeni
Sima E. Borujeni
SNSaideep Nannapaneni
Saideep Nannapaneni
NNNam H. Nguyen
Nam H. Nguyen
EBElizabeth C. Behrman
Elizabeth C. Behrman
JAMES E STECKJAMES E STECK
JAMES E STECK

31 January 2020 in Quantum Machine Intelligence
Verified
Journal Article
Closed access
PDF file
NNNam H. Nguyen
Nam H. Nguyen
EBElizabeth Behrman
Elizabeth Behrman
JAMES E STECKJAMES E STECK
JAMES E STECK

2 September 2019 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
NNNam H. Nguyen
Nam H. Nguyen
EBElizabeth Behrman
Elizabeth Behrman
MMMohamed A. Moustafa
Mohamed A. Moustafa
JAMES E STECKJAMES E STECK
JAMES E STECK
The power of quantum computers is still somewhat speculative. Although they are certainly faster than classical ones at some tasks, the class of problems they can efficiently solve has not been mapped definitively onto known classical complexity theory. This means that we do not know for which calculations there will be a ``quantum advantage,'' once an algorithm is found. One way to answer the question is to find those algorithms, but finding truly quantum algorithms turns out to be very difficult. In previous work, over the past three decades, we have pursued the idea of using techniques of machine learning to develop algorithms for quantum computing. Here, we compare the performance of standard real- and complex-valued classical neural networks with that of one of our models for a quantum neural network, on both classical problems and on an archetypal quantum problem: the computation of an entanglement witness. The quantum network is shown to need far fewer epochs and a much smaller network to achieve comparable or better results.

1 January 2013 in The Scientific World Journal
Verified
Journal Article
Open access
PDF file
ZKZachary Kral
Zachary Kral
WHWalter Horn
Walter Horn
JAMES E STECKJAMES E STECK
JAMES E STECK
Aerospace systems are expected to remain in service well beyond their designed life. Consequently, maintenance is an important issue. A novel method of implementing artificial neural networks and acoustic emission sensors to form a structural health monitoring (SHM) system for aerospace inspection routines was the focus of this research. Simple structural elements, consisting of flat aluminum plates of AL 2024‐T3, were subjected to increasing static tensile loading. As the loading increased, designed cracks extended in length, releasing strain waves in the process. Strain wave signals, measured by acoustic emission sensors, were further analyzed in post‐processing by artificial neural networks (ANN). Several experiments were performed to determine the severity and location of the crack extensions in the structure. ANNs were trained on a portion of the data acquired by the sensors and the ANNs were then validated with the remaining data. The combination of a system of acoustic emission sensors, and an ANN could determine crack extension accurately. The difference between predicted and actual crack extensions was determined to be between 0.004 in. and 0.015 in. with 95% confidence. These ANNs, coupled with acoustic emission sensors, showed promise for the creation of an SHM system for aerospace systems.

1 January 2000 in IEEE Transactions on Neural Networks
Verified
Journal Article
Closed access
SSS.R. Skinner
S.R. Skinner
JAMES E STECKJAMES E STECK
JAMES E STECK
EBElizabeth Behrman
Elizabeth Behrman
GCGuoqi Cui
Guoqi Cui
MYMingtao Yang
Mingtao Yang
ACA.A. Cruz-Cabrera
A.A. Cruz-Cabrera
The optical bench training of an optical feedforward neural network, developed by the authors, is presented. The network uses an optical nonlinear material for neuron processing and a trainable applied optical pattern as the network weights. The nonlinear material, with the applied weight pattern, modulates the phase front of a forward propagating information beam by dynamically altering the index of refraction profile of the material. To verify that the network can be trained in real time, six logic gates were trained using a reinforcement training paradigm. More importantly, to demonstrate optical backpropagation, three gates were trained via optical error backpropagation. The output error is optically backpropagated, detected with a CCD camera, and the weight pattern is updated and stored on a computer. The obtained results lay the ground work for the implementation of multilayer neural networks that are trained using optical error backpropagation and are able to solve more complex problems.