Open Access. Powered by Scholars. Published by Universities.®
Numerical Analysis and Scientific Computing
University of Arkansas, Fayetteville
Computer Science and Computer Engineering Undergraduate Honors Theses
- Keyword
-
- Bayesian Inference (1)
- Bioinformatics (1)
- ChipWhisperer (1)
- Computer vision (1)
- Foresight pruning (1)
-
- GloVe (1)
- Graph Neural Networks (1)
- Image classification (1)
- Leakage assessment (1)
- Markov Chain Monte Carlo (1)
- Masking (1)
- Microbiome (1)
- Natural language processing (1)
- Node Classification (1)
- Oscilloscope (1)
- Post-Quantum Cryptography (1)
- Qiime2 (1)
- Semi-Supervised Learning (1)
- Side-channel Analysis (1)
- Similarity analysis (1)
- Supervised learning (1)
- Synonyms (1)
- TruncTrimmer (1)
- Unstructured pruning (1)
- Word embedding (1)
- Word2Vec (1)
Articles 1 - 5 of 5
Full-Text Articles in Theory and Algorithms
Gauging The State-Of-The-Art For Foresight Weight Pruning On Neural Networks, Noah James
Gauging The State-Of-The-Art For Foresight Weight Pruning On Neural Networks, Noah James
Computer Science and Computer Engineering Undergraduate Honors Theses
The state-of-the-art for pruning neural networks is ambiguous due to poor experimental practices in the field. Newly developed approaches rarely compare to each other, and when they do, their comparisons are lackluster or contain errors. In the interest of stabilizing the field of pruning, this paper initiates a dive into reproducing prominent pruning algorithms across several architectures and datasets. As a first step towards this goal, this paper shows results for foresight weight pruning across 6 baseline pruning strategies, 5 modern pruning strategies, random pruning, and one legacy method (Optimal Brain Damage). All strategies are evaluated on 3 different architectures …
Side-Channel Analysis On Post-Quantum Cryptography Algorithms, Tristen Teague
Side-Channel Analysis On Post-Quantum Cryptography Algorithms, Tristen Teague
Computer Science and Computer Engineering Undergraduate Honors Theses
The advancements of quantum computers brings us closer to the threat of our current asymmetric cryptography algorithms being broken by Shor's Algorithm. NIST proposed a standardization effort in creating a new class of asymmetric cryptography named Post-Quantum Cryptography (PQC). These new algorithms will be resistant against both classical computers and sufficiently powerful quantum computers. Although the new algorithms seem mathematically secure, they can possibly be broken by a class of attacks known as side-channels attacks (SCA). Side-channel attacks involve exploiting the hardware that the algorithm runs on to figure out secret values that could break the security of the system. …
A Comparison Of Word Embedding Techniques For Similarity Analysis, Tyler Gerth
A Comparison Of Word Embedding Techniques For Similarity Analysis, Tyler Gerth
Computer Science and Computer Engineering Undergraduate Honors Theses
There have been a multitude of word embedding techniques developed that allow a computer to process natural language and compare the relationships between different words programmatically. In this paper, similarity analysis, or the testing of words for synonymic relations, is used to compare several of these techniques to see which performs the best. The techniques being compared all utilize the method of creating word vectors, reducing words down into a single vector of numerical values that denote how the word relates to other words that appear around it. In order to get a holistic comparison, multiple analyses were made, with …
Improving Bayesian Graph Convolutional Networks Using Markov Chain Monte Carlo Graph Sampling, Aneesh Komanduri
Improving Bayesian Graph Convolutional Networks Using Markov Chain Monte Carlo Graph Sampling, Aneesh Komanduri
Computer Science and Computer Engineering Undergraduate Honors Theses
In the modern age of social media and networks, graph representations of real-world phenomena have become incredibly crucial. Often, we are interested in understanding how entities in a graph are interconnected. Graph Neural Networks (GNNs) have proven to be a very useful tool in a variety of graph learning tasks including node classification, link prediction, and edge classification. However, in most of these tasks, the graph data we are working with may be noisy and may contain spurious edges. That is, there is a lot of uncertainty associated with the underlying graph structure. Recent approaches to modeling uncertainty have been …
Trunctrimmer: A First Step Towards Automating Standard Bioinformatic Analysis, Z. Gunner Lawless, Dana Dittoe, Dale R. Thompson, Steven C. Ricke
Trunctrimmer: A First Step Towards Automating Standard Bioinformatic Analysis, Z. Gunner Lawless, Dana Dittoe, Dale R. Thompson, Steven C. Ricke
Computer Science and Computer Engineering Undergraduate Honors Theses
Bioinformatic analysis is a time-consuming process for labs performing research on various microbiomes. Researchers use tools like Qiime2 to help standardize the bioinformatic analysis methods, but even large, extensible platforms like Qiime2 have drawbacks due to the attention required by researchers. In this project, we propose to automate additional standard lab bioinformatic procedures by eliminating the existing manual process of determining the trim and truncate locations for paired end 2 sequences. We introduce a new Qiime2 plugin called TruncTrimmer to automate the process that usually requires the researcher to make a decision on where to trim and truncate manually after …