Loading…
August 19-20 | San Diego, CA
View More Details  & Register Here
LZ

Ligeng Zhu

MIT
Research Assistant
Ligeng Zhu is a research assistant of Professor Song Han’s group at MIT. His research focuses on efficient machine learning, with a special interest in the design automation. His recent AutoML works aim to automatically search the optimal neural-net architecture for a specific task and hardware. He and Han Cai proposed ProxylessNAS -- the first NAS that reduces the search cost of NAS to normal training level while expressing significant improvement than the current industry standard.

His recent public speaking experience includes:
[05/19] ProxylessNAS - Direct Neural Architecture on Target Task and Hardware | Poster presentation at ICLR 2019
[05/19] Neural Architecture Design - History, Present and Future | Invited talk at UIUC Beckman Institute
[04/19] ProxylessNAS - Direct Neural Architecture on Target Task and Hardware | IBM AI Events
[04/18] Sparsely Aggregated Convolution Networks | Invited talk at Deephi Tech & Sensetime, Beijing, China
[12/17] Sparsely Aggregated Convolution Networks | Invited talk at UBC-SFU Vision
[04/17] Deep Learning Tutorial for Beginners | Introductive tutorial at Zhejiang University, Hangzhou, China