Group Members

Kevin Chu

Projects: PXRD, Quantitative Spectrometry, DermaML, PreML

Nicole Tin

Project: DermaML

Sofia Kwee

Project: DermaML

Akilan Paramasivam

Velexi Research Scholar (2024)

Project: PreML

This project aims to use information theory to predict the learnability of a dataset by analyzing its features and its target variable. We compared information theory quantities like mutual information to the accuracies of trained models, and the results show that a relationship exists between them.

Hannah Zhang

Velexi Research Scholar (2023)

Project: Application of Machine Learning for Hand Age Prediction

The goal of this project is to develop machine learning software that detects hand age from image data collected by the University of Iowa faculty and staff. An emphasis was placed on feature engineering and understanding the mechanisms behind which the machine learning model(s) obtained results.

April Zhang

Velexi Research Scholar (2022)

Project: DermaML

William Gvozdjak

Velexi Research Scholar (2021)

Project: Geometric Algebra Software Project

In this project, I work on a geometric algebra library in the Julia programming language.

Hristo Todorov

Research Science Institute^* (2021)

Project: Exploring Machine Learning Interpretability by Analyzing Tumor Suppressor Genetic Sequence Data

With the application of machine learning techniques to various fields (e.g. speech synthesis, healthcare), the problem of interpretability is gaining importance. Genomics seems to be a promising field for building interpretable machine learning models. We created machine learning approaches for analyzing raw tumor suppressor genetic sequence data, focusing specifically on determining reference genes from randomly extracted k-mers, which is a challenging task due to the data sparsity. Our results suggest that the encoding of the input data has a strong impact on the representations the models learn and that SHAP values are a useful tool for interpreting the behavior of convolutional neural networks trained on limited genomics data.

* To help support Research Science Institute (RSI) during the COVID-19 pandemic, Velexi hosted several RSI projects remotely.

Jackson Flowers

Research Science Institute^* (2020)

Project: Using Geometric Algebra to Estimate the Sparsity of Data and the Size of the Minimal Overcomplete Basis for Data through Observations

We examined datasets comprised of unions of linear subspaces, with the goal of bounding the minimum number of vectors needed to sparsely represent the data. We developed a procedure that results in a bound for this number in the case where the dimensions of these subspaces are distinct, and we found a number of bounds for this number given the dimensions of each of the subspaces.

* To help support Research Science Institute (RSI) during the COVID-19 pandemic, Velexi hosted several RSI projects remotely.

Srikar Munukutla

Velexi Research Scholar (2019, 2020)

Project: Machine Learning Approaches for Analysis of Reflectance Spectra

Verona Teo

Velexi STEAM Practicum (2020)

Project: Financial Analysis Automation Tools for Value Investors

This project aims to develop an explicit model or formula for the valuation of companies and stocks with the hopes of providing investors with automated stock suggestions and investment strategies.

Luke Bemish

Research Science Institute^* (2020)

Project: Modifications of Földiák’s Algorithm for Imbalanced Data

* To help support Research Science Institute (RSI) during the COVID-19 pandemic, Velexi hosted several RSI projects remotely.

Marvin Li

Research Science Institute^* (2020)

Project: Machine Learning Driven Design of Catalysts for the Water Gas Shift Reaction

In this project, I use a machine learning drive approach to find novel catalysts with desirable properties for the Water Gas Shift Reaction.

* To help support Research Science Institute (RSI) during the COVID-19 pandemic, Velexi hosted several RSI projects remotely.

Sabrina Bonifacio

Velexi STEAM Practicum (2019)

Project: Machine Learning Applications in Python