Title | ||
---|---|---|
Cocktail: Learn a Better Neural Network Controller from Multiple Experts via Adaptive Mixing and Robust Distillation |
Abstract | ||
---|---|---|
Neural networks are being increasingly applied to control and decision making for learning-enabled cyber-physical systems (LE-CPSs). They have shown promising performance without requiring the development of complex physical models; however, their adoption is significantly hindered by the concerns on their safety, robustness, and efficiency. In this work, we propose COCKTAIL, a novel design framew... |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/DAC18074.2021.9586148 | 2021 58th ACM/IEEE Design Automation Conference (DAC) |
Keywords | DocType | ISSN |
Weight measurement,Adaptive systems,Neural networks,Energy measurement,Reinforcement learning,Time measurement,Robustness | Conference | 0738-100X |
ISBN | Citations | PageRank |
978-1-6654-3274-0 | 1 | 0.37 |
References | Authors | |
0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yixuan Wang | 1 | 3 | 2.45 |
Chao Huang | 2 | 7 | 2.15 |
Zhilu Wang | 3 | 5 | 3.84 |
Xu Shichao | 4 | 5 | 3.16 |
Zhaoran Wang | 5 | 157 | 33.20 |
Qi Zhu | 6 | 727 | 60.59 |