About
**DFX4ML: enable Dynamic Function eXchange for Machine Learning** In resource-constrained edge computing applications like satellites, autonomous vehicles, and wearable devices, power efficiency and hardware limitations are critical. FPGAs offer reconfigurability, but large ML models often exceed their capacity. This project tackles the issue by enabling dynamic Function eXecution (DFX), allowing efficient use of FPGA resources.
I'm a master's student at Chulalongkorn University, currently interning at edgespAIce@CERN. My thesis project, KATHRYN, is a hybrid hardware design and simulation framework that aligns closely with my CERN work, both aiming to generate flexible and efficient hardware..
0:00:00 Slide 1
0:05:21 Slide 2
0:06:30 Slide 3
The talk
Credits and licence
- Institution
- CERN
- Department
- Summer Student Lecture Programme General
- Speaker
- Tanawin Devaveja
- Year
- 2025
- Language
- English
- Source
- CERN
- Licence
- CERN, as CERN states it. CERN's terms
- Attribution
- © CERN. CERN provides its audiovisual media free of charge for educational and informational use, credited to CERN; this lecture is shown in CERN's own player.
- Who can watch
- CERN gives no rating. Invisible Network shows it to Teens profiles and older, judged from what the source says about it. How courses are placed