papers

Publications (35)

cs.CV2022

Winograd Convolution for Deep Neural Networks: Efficient Point Selection

Syed Asad Alam, Andrew Anderson, Barbara Barabasz +1

Convolutional neural networks (CNNs) have dramatically improved the accuracy of tasks such as object recognition, image segmentation and interactive speech systems. CNNs require la…

cs.DS2015

Practical Algorithms for Finding Extremal Sets

Martin Marinov, Nicholas Nash, David Gregg

The minimal sets within a collection of sets are defined as the ones which do not have a proper subset within the collection, and the maximal sets are the ones which do not have a…

cs.DS2015

The Takeoff Towards Optimal Sorting Networks

Martin Marinov, David Gregg

A complete set of filters for the optimal-depth -input sorting network problem is such that if there exists an -input sorting network of depth then there exists one…

cs.DC2017

Mutual Inclusivity of the Critical Path and its Partial Schedule on Heterogeneous Systems

Aravind Vasudevan, David Gregg

The critical path of a group of tasks is an important measure that is commonly used to guide task allocation and scheduling on parallel computers. The critical path is the longest…

cs.CC2016

On the GI-Completeness of a Sorting Networks Isomorphism

Martin Marinov, David Gregg

The subitemset isomorphism problem is really important and there are excellent practical solutions described in the literature. However, the computational complexity analysis and c…

cs.SE2025

Industrial-Scale Neural Network Clone Detection with Disk-Based Similarity Search

Gul Aftab Ahmed, Muslim Chochlov, Abdul Razzaq +5

Code clones are similar code fragments that often arise from copy-and-paste programming. Neural networks can classify pairs of code fragments as clone/not-clone with high accuracy.…