A Johansen is a CS PhD candidate and seasoned software engineer with 11 years of experience specializing in machine learning and deep learning engineering. They contribute practical, hands-on TensorFlow tutorials and labs used for CNNs, RNNs, spatial transformers and sequence-to-sequence GRU models, demonstrating both instructional clarity and production-oriented implementation. Their GitHub work emphasizes reproducible exercises that bridge academic research and applied engineering, reflecting a focus on explainable training workflows for tasks like MNIST classification and sequence translation. Based in the United States, they blend doctoral-level research with extensive applied ML engineering, often translating complex model concepts into teachable code and exercises. An underappreciated strength is their ability to craft learning material that scales from classroom use to industry practice, indicating strong communication as well as technical depth.
Practical tutorials and labs for TensorFlow used by Nvidia, FFN, CNN, RNN, Kaggle, AE
Role in this project:
ML Engineer
Contributions:97 commits, 2 PRs, 89 pushes in 3 months
Contributions summary:A implemented and refined exercises related to TensorFlow, focusing on practical tutorials and labs for deep learning. The commits demonstrate work on building and training a Convolutional Neural Network (CNN) for image classification on the MNIST dataset, with exploration of spatial transformers. Furthermore, the user worked on a recurrent neural network (RNN) for a sequence-to-sequence translation task using a GRU-based Encoder-Decoder architecture.
Contributions:46 commits, 42 pushes, 1 branch in 1 year 1 month
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.