Timezone: »

 
Signature Activation: A Sparse Signal View for Holistic Saliency
Jose Tello Ayala · Akl Fahed · Weiwei Pan · Eugene Pomerantsev · Patrick Ellinor · Anthony Philippakis · Finale Doshi-Velez

@
in 3rd Workshop on Interpretable Machine Learning in Healthcare (IMLH) »
Event URL: https://openreview.net/forum?id=xtitv3kMTe »

The adoption of machine learning in healthcare calls for model transparency and explainability. In this work, we introduce Signature Activation, a saliency method that generates holistic and class-agnostic explanations for Convolutional Neural Networks' outputs. We exploit the sparsity of images and give theoretical explanation to justify our methods. We show the potential use of our method in clinical settings through evaluating its efficacy for aiding the detection of lesions in Coronary Angiorams.

Keywords: Healthcare · Interpretability · saliency · model explanation

Author Information

Jose Tello Ayala (Harvard University)
Akl Fahed
Weiwei Pan (Harvard University)
Eugene Pomerantsev
Patrick Ellinor
Anthony Philippakis (Broad Institute)
Finale Doshi-Velez (Harvard University)
Finale Doshi-Velez

Finale Doshi-Velez is a Gordon McKay Professor in Computer Science at the Harvard Paulson School of Engineering and Applied Sciences. She completed her MSc from the University of Cambridge as a Marshall Scholar, her PhD from MIT, and her postdoc at Harvard Medical School. Her interests lie at the intersection of machine learning, healthcare, and interpretability. Selected Additional Shinies: BECA recipient, AFOSR YIP and NSF CAREER recipient; Sloan Fellow; IEEE AI Top 10 to Watch

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors