Kentaro Yoshioka is an associate professor at Keio University and a Ph.D. electrical engineer with eight years of experience at the intersection of efficient hardware, ML systems, and LiDAR technology. He combines hands-on analog and digital circuit design—authoring award-winning ADC and LiDAR SoC work at Toshiba and ISSCC—with scalable machine learning system builds and in-sensor accelerator research from his Stanford visiting scholar role. A Kaggle Master since 2020 and an active contributor to ML code (e.g., a Vision Transformer implementation for CIFAR-10), he uniquely bridges algorithmic ML practice and transistor-level hardware innovation. He has a track record of patents and top-conference publications and currently recruits for mixed-signal AI accelerator, LiDAR, and high-performance ADC projects at Keio.
8 years of coding experience
11 years of employment as a software developer
Doctor of Philosophy (Ph.D.), Electrical Engineering, Doctor of Philosophy (Ph.D.), Electrical Engineering at Keio University
Let's train vision transformers (ViT) for cifar 10!
Role in this project:
ML Engineer
Contributions:4 releases, 61 commits, 18 PRs in 1 year 10 months
Contributions summary:Kentaro implemented a Vision Transformer (ViT) model and training scripts for the CIFAR-10 dataset. They added the ViT model definition, incorporating components like attention, feedforward layers, and positional embeddings. The user also integrated the training script, loss functions and optimizers. Additional commits added logging, results logging, and made the kernel size configurable.
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.