Highlights include MFEM community workshops, compiler co-design, HPC standards committees, and AI/ML for national security.
Topic: Computer Vision
AI/ML | Biology/Biomedicine | Co-Design | Collaborations | Compiler Technology | Computational Math | Computational Science | Computer Vision | Data Science | Deep Learning | Discrete Mathematics | HPC Systems and Software | Natural Language Processing | Open-Source Software | Performance, Portability, and Productivity | Programming Languages and Models
The 2021 Conference on Computer Vision and Pattern Recognition features two papers co-authored by an LLNL researcher targeted at understanding robust machine learning models.
An LLNL-led team developed a new kind of prior—a characterization of the space of natural images—for compressive image recovery that is trained on patches of images instead of full-sized images.
Rushil Anirudh describes the machine learning field as undergoing a “gold rush.”