Machine learning researcher and engineer with experience in computer vision, time-series data analysis and forecasting, and natural language processing. I am passionate about building reliable ML systems for real-world use and conducting research on new learning algorithms. Concerning the recent AI literature, I am particularly interested in online learning and transformers for sequence modeling, video prediction, and generative AI. 🧑💻 🤖 I completed a Ph.D. at the University of Tokyo on respiratory motion forecasting with RNNs and transformers, and had the chance to investigate exciting physics and AI R&D problems across multiple industries (oil & gas, finance, healthcare, identity & security). I have been living in Japan for more than six years before moving to the UK. 🏯 💂♂️ Please do not hesitate to contact me for any matter, and let me know if I can help you. I am happy to connect and exchange ideas with like-minded tech professionals as well as computer science and ML enthusiasts.
| Chest cine MR sequence prediction using PCA and online learning of RNNs | Deformable 3D image registration with Lucas-Kanade pyramidal optical flow |
|---|---|
|
Prediction of dynamic sagittal MR cross-sections 6 time steps in advance using sparse 1-step approximation (left: ground-truth, right: prediction).  |
Calculation of the 3D motion of a lung tumor due to breathing using optical flow.  |
| Time series forecasting with online learning of recurrent neural networks | |
|
Prediction of the 3D position of 3 markers placed on the chest 2.1s (7 time steps) in advance using decoupled neural interfaces (the sampling rate is 3.33Hz) to guide the radiation beam during lung radiotherapy.  |
|