most citedImproving the Interpretability of Deep Neural Networks with Knowledge Distillation

11 citations · 11 across the 1 of their papers we have counts for

collaborators

2 papers

cs.LG2018★ 11 cited

Improving the Interpretability of Deep Neural Networks with Knowledge Distillation

Xuan Liu, Xiaoguang Wang, Stan Matwin

Deep Neural Networks have achieved huge success at a wide spectrum of applications from language modeling, computer vision to speech recognition. However, nowadays, good performanc…

cs.LG2018

Interpretable Deep Convolutional Neural Networks via Meta-learning

Xuan Liu, Xiaoguang Wang, Stan Matwin

Model interpretability is a requirement in many applications in which crucial decisions are made by users relying on a model's outputs. The recent movement for "algorithmic fairnes…