Stephen Welch
Founder at WelchLabs
Winston-Salem, North Carolina, United States
Summary
🤩
Rockstar🎓
Top SchoolStephen Welch is a founder and machine learning/vision engineering leader based in Winston-Salem with 11 years of experience who built Welch Labs into a 50M+ view, 550k+ subscriber educational channel translated into 25+ languages. He pairs creator-grade teaching with enterprise delivery—architecting Spyglass Visual Inspection as VP Data Science at Mariner, a distributed deep-learning quality system that delivered over $8M/year in customer value and helped earn Microsoft’s 2020 Global IoT Partner award. Stephen has shipped production ML systems at startups (Invisible AI, Autonomous Fusion), building annotation tools, training pipelines in PyTorch/TensorFlow, and lightweight, rapid-inference models. His hands-on work ranges from implementing and validating neural networks (see Neural-Networks-Demystified with numerical gradient checks) to deploying real-time ML on XMOS DSPs for audio pickup design and co-authoring multiple patent filings. He also teaches graduate computer vision courses and runs industry partnership programs, blending clear technical communication with practical productization.
12 years of coding experience
15 years of employment as a software developer
M.S., Environmental Engineering, 3.89, M.S., Environmental Engineering, 3.89 at University of California, BerkeleyB.S., Electrical Engineering, 3.87, B.S., Electrical Engineering, 3.87 at Georgia Institute of Technology
English
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (6)
neural-network10
machine-learning10
gradient-descent10
python10
backpropagation10
numpy10
Programming languages (4)
Github contributions (5)
stephencwelch/Neural-Networks-Demystified
Jan 2015 - Mar 2020
Supporting code for short YouTube series Neural Networks Demystified.
Role in this project:
ML Engineer
ML EngineerContributions:36 commits, 9 PRs, 36 pushes in 5 years 3 months
Contributions summary:Stephen primarily contributed to the development of the neural network project by adding and updating code related to forward propagation, gradient descent, and backpropagation, which are all fundamental concepts in neural networks. They implemented methods and functions, including activation functions, and cost calculations, while fixing errors. The user also incorporated a numerical gradient-checking process to validate the implementation and ensure accurate results, and ultimately trained the network.
youtube-seriesdeep-learningneural-networksmachine-learningshort
stephencwelch/Neural-Networks-For-Audio-Processing
Feb 2015 - Aug 2017
Contributions:35 commits, 32 pushes, 1 branch in 2 years 6 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.