Alex Williams
Neuroscience PhD Student at Stanford University
New York, New York, United States
Summary
👤
Senior🎓
Top SchoolAlex Williams is a Neuroscience PhD student and researcher based in New York with 13 years of experience bridging experimental neuroscience and computational methods. Trained at Bowdoin College and currently at Stanford, Alex contributes to open-source tools for state-space modeling—improving cross-validation, log-likelihood, and model-selection utilities in the widely used lindermanlab/ssm library. His work blends hands-on lab experience from roles at Brandeis and UC San Diego with rigorous probabilistic modeling, enabling more reliable evaluation of HMM and HSMM workflows. Known for tackling under-the-hood diagnostic problems, he brings pragmatic engineering to neuroscience questions, making complex inference pipelines more robust and reproducible.
13 years of coding experience
Niskayuna High SchoolBachelor of Arts, Neuroscience, Bachelor of Arts, Neuroscience at Bowdoin College
Github Skills (12)
variable-selection10
state-space10
python10
hmmlearn10
multiple-selection10
feature-selection10
numpy10
cross-validation10
autograd9
machine-learning9
scikit8
scikit-learn8
Programming languages (8)
Github contributions (5)
lindermanlab/ssm
Jun 2019 - Sep 2021
Bayesian learning and inference for state space models
Role in this project:
Data Scientist
Data ScientistContributions:7 commits, 3 PRs, 3 pushes in 2 years 3 months
Contributions summary:Alex contributed to the development and refinement of cross-validation functionalities within the ssm library. Their work involved implementing and fixing components related to model evaluation, particularly focusing on the log-likelihood calculation and expected log-likelihood computations for Hidden Markov Models (HMMs) and Semi-Markov models (HSMMs). This includes changes in the `model_selection.py` file, suggesting a focus on model selection and diagnostic tools for state-space models. Furthermore, they made modifications to `hmm.py` and `ssm/observations.py` to facilitate the implementation and debugging of various cross-validation methods and features.
bayesianinferencestate-space
JuliaLinearAlgebra/NonNegLeastSquares.jl
Oct 2015 - May 2019
Some nonnegative least squares solvers in Julia
Contributions:74 commits, 12 PRs, 65 pushes in 3 years 8 months
julialeast-squares
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.