Bethany Lusch
Computer Scientist at Argonne Leadership Computing Facility
Lemont, Illinois, United States
Summary
👤
Senior🎓
Top SchoolBethany Lusch is a computer scientist at Argonne Leadership Computing Facility with 11 years of experience applying machine learning and optimization to complex scientific systems. Her work spans algorithms for document summarization, dimensionality reduction and coordinate transforms that simplify control, and approximations of optimization problems underpinning ML, with applications from neuroscience to fluid dynamics and crime-pattern discovery. At Argonne she develops data-driven methods for science at scale, including hands-on ML training materials such as an MNIST MLP notebook for the ALCF ai-science training series. She combines deep academic training (PhD, University of Washington) with practical supercomputing experience, translating theory into tools that run on national-scale compute resources.
11 years of coding experience
6 years of employment as a software developer
MS, MS at University of WashingtonRosary High SchoolBS, BS at University of Notre DameBudapest Semesters in Mathematics
Github Skills (8)
neural-network10
machine-learning10
tensorflow10
python10
mnist10
numpy10
keras9
computer-engineering8
Programming languages (4)
Github contributions (5)
argonne-lcf/ai-science-training-series
Feb 2022 - Nov 2022
Role in this project:
Data Scientist
Data ScientistContributions:1 release, 34 commits, 12 PRs in 9 months
Contributions summary:Bethany's primary contribution involves developing a notebook focused on MNIST handwritten digit classification using Multi-Layer Perceptrons (MLPs). The user implemented a linear model and then explored improvements by implementing sigmoid and softmax activations, and also the creation of a full network for a multi-layer perceptron. The user is also working on implementing regularizations, and evaluating performance with accuracy metrics and visualized plots of losses.
BethanyL/DeepKoopman
Jan 2018 - Nov 2021
neural networks to learn Koopman eigenfunctions
Contributions:2 releases, 79 commits, 41 pushes in 3 years 10 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.