Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Interpretations are useful: penalizing explanations to align neural networks with prior knowledge



Laura Rieger , Chandan Singh , W. James Murdoch , Bin Yu


   Access Paper or Ask Questions

Disentangled Attribution Curves for Interpreting Random Forests and Boosted Trees



Summer Devlin , Chandan Singh , W. James Murdoch , Bin Yu

* Under review 

   Access Paper or Ask Questions

Interpretable machine learning: definitions, methods, and applications



W. James Murdoch , Chandan Singh , Karl Kumbier , Reza Abbasi-Asl , Bin Yu

* 11 pages 

   Access Paper or Ask Questions

Hierarchical interpretations for neural network predictions



Chandan Singh , W. James Murdoch , Bin Yu

* main text: 8 pages, references: 2 pages, supplement: 13 pages 

   Access Paper or Ask Questions

Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs



W. James Murdoch , Peter J. Liu , Bin Yu

* Oral presentation at ICLR 2018 

   Access Paper or Ask Questions

Automatic Rule Extraction from Long Short Term Memory Networks



W. James Murdoch , Arthur Szlam

* ICLR 2017 accepted paper 

   Access Paper or Ask Questions

Expanded Alternating Optimization of Nonconvex Functions with Applications to Matrix Factorization and Penalized Regression



W. James Murdoch , Mu Zhu


   Access Paper or Ask Questions