S
Stephen D. Scott
Researcher at University of Nebraska–Lincoln
Publications - 78
Citations - 1603
Stephen D. Scott is an academic researcher from University of Nebraska–Lincoln. The author has contributed to research in topics: Instance-based learning & Winnow. The author has an hindex of 22, co-authored 76 publications receiving 1451 citations. Previous affiliations of Stephen D. Scott include Washington University in St. Louis & Lincoln University (Pennsylvania).
Papers
More filters
Proceedings ArticleDOI
HGA: A Hardware-Based Genetic Algorithm
TL;DR: A fully functional hardware-based genetic algorithm (the HGA) is presented here as a proof-of-concept system designed using VHDL to allow for easy scalability and compared to a similar GA implemented in software.
Proceedings ArticleDOI
Balancing exploration and exploitation: a new algorithm for active machine learning
TL;DR: This work proposes a new active learning algorithm that balances exploration with refining of the decision boundary by dynamically adjusting the probability to explore at each step, and demonstrates improved performance on data sets that require extensive exploration while remaining competitive on data set that do not.
Proceedings ArticleDOI
SVM-based generalized multiple-instance learning via approximate box counting
TL;DR: This work reformulates a generalization of the multiple-instance learning model using a kernel for a support vector machine, reducing its time complexity from exponential to polynomial, and gives a fullyPolynomial randomized approximation scheme (FPRAS) for it.
Journal ArticleDOI
Comparison of Object Detection and Patch-Based Classification Deep Learning Models on Mid- to Late-Season Weed Detection in UAV Imagery
Arun Narenthiran Veeranampalayam Sivakumar,Jiating Li,Stephen D. Scott,Eric T. Psota,Amit J. Jhala,Joe D. Luck,Yeyin Shi +6 more
TL;DR: Faster RCNN was found to be the best model in terms of weed detection performance and inference time among the different models compared in this study.
Journal ArticleDOI
On-line analysis of the TCP acknowledgment delay problem
TL;DR: This work describes an on-line algorithm that greedily acknowledges exactly when the cost for an acknowledgment is less than the latency cost incurred by not acknowledging, and shows that for each objective function, at least one of the algorithms is optimal.