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

Published in arXiv preprint arXiv:1909.13584, 2019

Recommended citation: Laura Rieger, Chandan Singh, W Murdoch, Bin Yu, "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge." arXiv preprint arXiv:1909.13584, 2019.

Use Google Scholar for full citation