Interpreting, Explaining and Visualizing Deep Learning
... now what ?
NIPS 2017 Workshop, 9 December 2017, Long Beach, CA

List of Speakers | Call for Papers | Tentative Schedule | Organizers ]

While machine learning models have reached impressively high predictive accuracy, they are often perceived as black-boxes. In sensitive applications such as medical diagnosis or self-driving cars, the reliance of the model on the right features must be guaranteed. One would like to be able to interpret what the ML model has learned in order to identify biases and failure modes and improve models accordingly. Interpretability is also needed in the sciences, where understanding how the ML model relates the multiple physical and biological variables is a prerequisite for building meaningful scientific hypotheses.

The present workshop aims to review recent techniques and establish new theoretical foundations for interpreting and understanding deep learning models. However, it will not stop at the methodological level, but also address the “now what?” question, where we aim to take the next step by exploring and extending practical usefulness. The workshop will have speakers from various application domains (computer vision, NLP, neuroscience, medicine), it will provide an opportunity for participants to learn from each other and initiate new interdisciplinary collaborations.

List of Speakers

  • Dhruv Batra
    Georgia Tech

  • Rich Caruana

  • Trevor Darrell
    UC Berkeley

  • Marcel van Gerven
    Radboud University

  • Sepp Hochreiter
    University Linz

  • Been Kim
    Google Brain

  • Honglak Lee
    University of Michigan

  • Anh Nguyen
    Auburn University

Call for Papers

We call for papers on the following topics: (1) interpretability of deep neural networks, (2) analysis and comparison of state-of-the-art models, (3) formalization of the interpretability problem, (4) interpretability for making ML socially acceptable, and (5) applications of interpretability.

Submissions are required to stick to the NIPS format. Papers are limited to eight pages (excluding references) and will go through a review process. A selection of accepted papers together with the invited contributions will be part of an edited book at Springer LNCS.
Submission website:
Important dates
Submission deadline 22 October, 2017
Author notification 01 November, 2017
Workshop 09 December, 2017

Tentative Schedule

Session 1: Foundations
08.30 - 09.00Opening Remarks
09.00 - 09.30Invited Talk 1
09.30 - 10.00Invited Talk 2
10.00 - 10.30Methods Talks (2x15 min)
10.30 - 11.00Coffee Break
11:00 - 11.30Invited Talk 3
11.30 - 12.00Methods Talks (3x10 min)
12.00 - 12.30Posters + Demonstrations
12:30 - 13.30Lunch
Session 2: Applications
13.30 - 14.00Posters + Demonstrations
14.00 - 14.30Invited Talk 4
14.30 - 15.00Invited Talk 5
15.00 - 15.30Coffee Break
15.30 - 16:00Application Talks (3x10 min)
16.00 - 16.30Invited Talk 6
16.30 - 17.00Invited Talk 7
17.00 - 17:30Application Talks (2x15 min)
17.30 - 18:15Panel Discussion / Closing Remarks