Bill Lotter
Assistant Professor, Department Of Data Science
Greater Boston United States
Summary
👤
Senior🎓
Top SchoolBill Lotter is an Assistant Professor of Data Science at Dana-Farber Cancer Institute and Harvard Medical School with a decade of experience building and deploying machine learning systems in clinical and commercial settings. He co-founded and served as CTO of DeepHealth, leading development of two FDA-cleared AI products that now process over one million mammograms annually and were commercialized after acquisition by RadNet. His background spans high-frequency algorithmic trading, sports analytics for an NFL franchise, and hands-on ML engineering (including work on the influential PredNet video-prediction model), reflecting a rare blend of academic rigor and product delivery. Bill holds a PhD in Biophysics with a secondary field in Computational Science from Harvard and multiple degrees in math and integrated science from Northwestern, underscoring deep quantitative expertise. He is drawn to translating advanced models into regulated, real-world impact—often tackling the messy engineering and validation work that gets research into production.
10 years of coding experience
8 years of employment as a software developer
PhD, Biophysics, Secondary Field in Computational Science, PhD, Biophysics, Secondary Field in Computational Science at Harvard UniversityMS, BA, BA, Applied Math, Math, Integrated Science, MS, BA, BA, Applied Math, Math, Integrated Science at Northwestern University
Github Skills (14)
keras10
computer-vision10
machine-learning10
deep-learning10
python10
modeling9
trainings9
evaluation9
eval9
recurrent-neural-networks8
convolutional-neural-networks8
neural-network8
tensorflow7
data-processing7
Programming languages (1)
Github contributions (5)
coxlab/prednet
Jul 2016 - Mar 2019
Code and models accompanying "Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning"
Role in this project:
ML Engineer
ML EngineerContributions:87 commits, 9 PRs, 29 pushes in 2 years 8 months
Contributions summary:Bill primarily focused on developing and refining the PredNet model, a deep learning architecture for video prediction. Their contributions included implementing and debugging the core PredNet architecture in Python using Keras. The user also made changes to the training and evaluation scripts for the model and adapted the code for the KITTI dataset. Furthermore, they added features for extrapolating video frames, demonstrating expertise in model customization and experimentation.
pytorchvideo-predictionpredictionunsupervised-learningdeep-learning
bill-lotter/keras
Mar 2016 - Jun 2018
Contributions:60 pushes, 5 branches in 2 years 3 months
pythondeep-learningrecurrent-neural-networkstheanoneural-networks
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.