Search

Ninghao Liu

Techniques for Interpretable Machine Learning
Learning Credible DNNs via Incorporating Prior Knowledge and Model Local Explanation
An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networks
Learning Credible Deep Neural Networks with Rationale Regularization
On Attribution of Recurrent Neural Network Predictions via Additive Decomposition
Towards Explanation of DNN-based Prediction with Guided Feature Inversion

Published with Wowchemy — the free, open source website builder that empowers creators.