Publications (6)
RESPECT: Reinforcement Learning based Edge Scheduling on Pipelined Coral Edge TPUs
Jiaqi Yin, Yingjie Li, Daniel Robinson +1
Deep neural networks (DNNs) have substantial computational and memory requirements, and the compilation of its computational graphs has a great impact on the performance of resourc…
Precise Matching of PL Curves in in the Square Root Velocity Framework
Sayani Lahiri, Daniel Robinson, Eric Klassen
The square root velocity function (SRVF), introduced by Srivastava et al, has proved to be an effective way to compare absolutely continuous curves in modulo reparametrizatio…
Searching for Inflow Towards Massive Starless Clump Candidates Identified in the Bolocam Galactic Plane Survey
Jenny Calahan, Yancy Shirley, Brian Svoboda +22
Recent Galactic plane surveys of dust continuum emission at long wavelengths have identified a population of dense, massive clumps with no evidence for on-going star formation. The…
MapTune: Advancing ASIC Technology Mapping via Reinforcement Learning Guided Library Tuning
Mingju Liu, Daniel Robinson, Yingjie Li +1
Technology mapping involves mapping logical circuits to a library of cells. Traditionally, the full technology library is used, leading to a large search space and potential overhe…
All-Optical Segmentation via Diffractive Neural Networks for Autonomous Driving
Yingjie Li, Daniel Robinson, Weilu Gao +1
Semantic segmentation and lane detection are crucial tasks in autonomous driving systems. Conventional approaches predominantly rely on deep neural networks (DNNs), which incur hig…
Negative Curvature and Second-order optimality for regularized SQP
Phillip Gill, Vyacheslav Kungurtsev, Daniel Robinson
Negative Curvature and Second-order optimality for regularized SQP