<div dir="ltr"><p class="gmail-p1">=============================<br></p><p class="gmail-p1"><span class="gmail-s1">Call for Papers: NIPS 2017 Symposium<br></span>Interpretable Machine Learning<br>Website: <span class="gmail-s3"><a href="http://interpretable.ml/">http://interpretable.ml</a><br></span>Location: Long Beach, California, USA<br>Date: December 7, 2017</p><p class="gmail-p1"><span class="gmail-s1">=============================</span></p><p class="gmail-p1"><span class="gmail-s5">Call for Papers:</span><span class="gmail-s4"><br></span></p><p class="gmail-p1"><span class="gmail-s1">We invite researchers to submit their recent work on interpretable machine learning from a wide range of approaches, including (1) methods that are designed to be more interpretable from the start, such as rule-based methods, (2) methods that produce insight into existing ML models, and (3) perspectives either for or against interpretability in general. Topics of interest include:</span></p><ul class="gmail-ul1"><li class="gmail-li4"><span class="gmail-s6"></span><span class="gmail-s4">Deep learning</span></li><li class="gmail-li4"><span class="gmail-s4">Kernel, tensor, graph, or probabilistic methods</span></li><li class="gmail-li4"><span class="gmail-s4">Automatic scientific discovery</span></li><li class="gmail-li4"><span class="gmail-s4">Safe AI and AI Ethics</span></li><li class="gmail-li4"><span class="gmail-s4">Causality</span></li><li class="gmail-li4"><span class="gmail-s4">Social Science</span></li><li class="gmail-li4"><span class="gmail-s4">Human-computer interaction</span></li><li class="gmail-li4"><span class="gmail-s4">Quantifying or visualizing interpretability</span></li><li class="gmail-li4"><span class="gmail-s4">Symbolic regression</span></li></ul><p class="gmail-p1"><span class="gmail-s1">Authors are welcome to submit 2-4 page extended abstracts, in the NIPS style. Author names do not need to be anonymized. Accepted papers will have the option of inclusion in the proceedings. Certain papers will also be selected to present spotlight talks. Email submissions to <a href="mailto:interpretML2017@gmail.com"><span class="gmail-s3">interpretML2017@gmail.com</span></a></span><span class="gmail-s7">.</span></p><p class="gmail-p1"><span class="gmail-s1">Key Dates:<br></span><b>Submission Deadline: 20 Oct 2017<br></b>Acceptance Notification: 27 Oct 2017<br>Symposium: 7 Dec 2016</p><p class="gmail-p1"><span class="gmail-s5">Speakers and Panelists:</span></p><p class="gmail-p1"></p><ul><li>Kilian Weinberger (Cornell)<br></li><li>Jerry Zhu (UW-Madison)<br></li><li>Viktoria Krakovna (DeepMind)<br></li><li>Bernhard Scholkopf (MPI)<br></li><li>Kiri Wagstaff (JPL)<br></li><li>Suchi Saria (JHU)<br></li><li>Jenn Vaughan (Microsoft)<br></li><li>Yann LeCun (NYU)<br></li><li>Hanna Wallach (Microsoft)</li></ul><p></p><p class="gmail-p1"><span class="gmail-s5">Organizers:</span></p><p class="gmail-p1"></p><ul><li>Andrew Gordon Wilson (Cornell)<br></li><li>Jason Yosinski (Uber AI Labs)<br></li><li>Patrice Simard (Microsoft)<br></li><li>Rich Caruana (Microsoft)<br></li><li>William Herlands (CMU)</li></ul><p></p><p class="gmail-p1"><span class="gmail-s5">Workshop Overview:</span><span class="gmail-s4"><br></span></p><p class="gmail-p5"><span class="gmail-s4">Complex machine learning models, such as deep neural networks, have recently achieved outstanding predictive performance in a wide range of applications, including visual object recognition, speech perception, language modeling, and information retrieval. There has since been an explosion of interest in interpreting the representations learned and decisions made by these models, with profound implications for research into explainable ML, causality, safe AI, social science, automatic scientific discovery, human computer interaction (HCI), crowdsourcing, machine teaching, and AI ethics. This symposium is designed to broadly engage the machine learning community on the intersection of these topics -- tying together many threads which are deeply related but often considered in isolation.</span></p><p class="gmail-p6"><span class="gmail-s1">For example, we may build a complex model to predict levels of crime. Predictions on their own produce insights, but by interpreting the learned structure of the model, we can gain more important new insights into the processes driving crime, enabling us to develop more effective public policy. Moreover, if we learn that the model is making good predictions by discovering how the geometry of clusters of crime events affect future activity, we can use this knowledge to design even more successful predictive models. Similarly, if we wish to make AI systems deployed on self-driving cars safe, straightforward black-box models will not suffice, as we will need methods of understanding their rare but costly mistakes.</span><span class="gmail-s4"><br><br></span><span class="gmail-s1">The symposium will feature invited talks and two panel discussions. One of the panels will have a moderated debate format where arguments are presented on each side of key topics chosen prior to the symposium, with the opportunity to follow-up each argument with questions. This format will encourage an interactive, lively, and rigorous discussion, working towards the shared goal of making intellectual progress on foundational questions. During the symposium, we will also feature the launch of a new Explainability in Machine Learning Challenge, involving the creation of new benchmarks for motivating the development of interpretable learning algorithms.</span></p><br><br><br><br><div><div class="gmail_signature">best,<div><div class="gmail_signature" data-smartmail="gmail_signature">jason<br><br><br>---------------------------<br>Jason Yosinski <a href="http://yosinski.com/" target="_blank">http://yosinski.com/</a> +1.719.440.1357</div></div>
</div></div>
</div>