Tue22Jan201911:30 amEhrlicher Room
MISC will kick off the winter term with lightning talks from our faculty on campus. Nia Dowell, Mustafa Naseem, Audrey Bennett, and Nikola Banovic will be giving a brief introduction of their research.
On Tuesday 2/12, Samuel Carton, a PhD Candidate from the School of Information will present his work on “The Design and Evaluation of Algorithms for Explaining Text Classifiers”
Please help forward this announcement to anyone who might be interested! Light lunch will be provided.
Please RSVP by 12 PM on 2/10 if you will be there.
The machine learning community has recently begun to recognize the need for interpretable predictive models. While such models can be trained to be very accurate, sometimes even more accurate than their human counterparts on average, they have a tendency to fail unexpectedly and are ill-equipped to deal with nuance and outliers. One of the biggest challenges in this area is in defining what it means for an explanation to be effective in the first place, and then in designing algorithms optimized for this quality. In this talk I discuss two papers: the first is an algorithm for explaining text classifier decisions by producing high-recall attention masks, and the second is a crowdsourced experiment exploring the impact of this type of explanation on human performance in a model-assisted decision task.
Sam is a PhD candidate in the school of information, advised by Paul Resnick and Qiaozhu Mei. He received a BS in computer science from Northwestern University. Sam's current research interests are in explainable machine learning, where he is interested both in engineering new explanation methods as well as understanding the human factors that determine what explanations are effective in real-world settings. His past work includes projects on tracking and visualizing the spread of rumors over social media as well as predictive modeling of police misconduct. His professional experience includes an internship with Microsoft Research as well as the Data Science for Social Good Fellowship at the University of Chicago.
When and where:
February 19, 11:30 AM, North Quad, Ehrlicher Room (room 3100) (add to calendar)
Light lunch will be provided at 11:30 AM. The talk will begin at noon.
Please RSVP by 12 PM on 2/17 if you will be there.
Abstract: Many students in large survey courses are reluctant to pose verbal questions during class. Entreating students with “Any questions?” more often than not fails to produce a response and, when it does, comes from a small subset of all students. This presentation reports on the use of a backchannel in a blended course and how the backchannel affected student participation based on a priori comfort level with verbal questioning.
The use of a backchannel increased student inquiry in class dramatically but, more importantly, its use virtually eliminated the gender bias in student inquiry often seen in science courses. It was found that the use of a backchannel had a significant positive effect on the level of participation by female students who had professed a greater discomfort with verbal questioning in the initial course survey. Additionally, a longitudinal study was conducted to identify students’ perceived value of the backchannel to improving verbal participation in subsequent courses. The longitudinal survey showed that a majority felt strongly that the availability of the backchannel was highly valuable and its availability in the first-year course changed their willingness to ask verbal questions in subsequent courses.
Bio: Perry Samson is an Arthur Thurnau Professor at the University of Michigan with appointments in the College of Engineering and the School of Information. Prof. Samson teaches courses in extreme weather and climate and air pollution modeling. Perry is also an entrepreneur as a co-founder of The Weather Underground and LectureTools and serves as a mentor for education technology internships.