Bryce Murray
University of Missouri
15 Papers
32 Citations
Bryce Murray is an academic researcher from University of Missouri. The author has contributed to research in topics: Deep learning & Computer science. The author has an hindex of 5, co-authored 15 publications. Previous affiliations of Bryce Murray include Mississippi State University.
Chat about Author
Papers
Fuzzy Choquet Integration of Deep Convolutional Neural Networks for Remote Sensing
Derek T. Anderson,Grant J. Scott,Muhammad Aminul Islam,Bryce Murray,Richard A. Marcum +4 more
- 01 Jan 2018
TL;DR: This work explores the advantage of data-driven optimization of fusing different deep nets–GoogleNet, CaffeNet and ResNet–at a per class (neuron) or shared weight (single data fusion across classes) fashion and shows that fusion is the top performer.
37
Explainable AI for the Choquet Integral
Bryce Murray,Muhammad Aminul Islam,Anthony J. Pinar,Derek T. Anderson,Grant J. Scott,Timothy C. Havens,James M. Keller +6 more
- 01 Aug 2021
TL;DR: This work makes XAI more accurate by taking into consideration what the machine learned, and a combination of synthetic data and real-world experiments from remote sensing for fusing deep learners in the context of classification are explored.
37
Survey and Insights into Unmanned Aerial-Vehicle-Based Detection and Documentation of Clandestine Graves and Human Remains
TL;DR: This article focuses on detecting and documenting terrestrial clandestine graves and surface remains (CGSR) of humans using unmanned aerial vehicles (UAVs), sensors, and automatic processing algorithms.
Explainable AI for Understanding Decisions and Data-Driven Optimization of the Choquet Integral
Bryce Murray,M. Aminul Islam,Anthony J. Pinar,Timothy C. Havens,Derek T. Anderson,Grant J. Scott +5 more
- 08 Jul 2018
TL;DR: Methods for XAI of the Choquet integral (ChI), a parametric nonlinear aggregation function, are discussed, and existing indices are reviewed, and new data-centric XAI tools are introduced.
23
Extending the Morphological Hit-or-Miss Transform to Deep Neural Networks
Muhammad Aminul Islam,Bryce Murray,Andrew Buck,Derek T. Anderson,Grant J. Scott,Mihail Popescu,James M. Keller +6 more
TL;DR: In this paper, the intersection of the hit and miss structuring elements (SEs) should be empty and present a way to express Don't Care (DNC), which is important for denoting regions of an SE that are not relevant to detecting a target pattern.
15