3 papers
cs.LG2022
WeShort: Out-of-distribution Detection With Weak Shortcut structure
Jinhong Lin
Neural networks have achieved impressive performance for data in the distribution which is the same as the training set but can produce an overconfident incorrect result for the da…
cs.LG2021
Extracting knowledge from features with multilevel abstraction
Jinhong Lin, Zhaoyang Li
Knowledge distillation aims at transferring the knowledge from a large teacher model to a small student model with great improvements of the performance of the student model. There…
cs.LG2021
Toward Robust Long Range Policy Transfer
Wei-Cheng Tseng, Jin-Siang Lin, Yao-Min Feng +1
Humans can master a new task within a few trials by drawing upon skills acquired through prior experience. To mimic this capability, hierarchical models combining primitive policie…