This event will be Livestreamed here:|
Despite the fact that neural network models outperform other approaches to text classification problems, some data scientists still hesitate to use them based on the assumption that interpreting the models decisions is impossible. In this talk, I will discuss the difference between global & local interpretability; what these concepts mean in the context of text classification models; & how to use two specific local interpretability methods, saliency & occlusion, to open the black box of a neural network. I will also touch on hierarchical attention networks, a neural network text classification model with built-in local interpretability in the form of attention.
Rebecca Jones is Data Scientist at Allstate Insurance Company, specializing in Natural Language Processing for the past two years. She has a graduate degree in Applied Mathematics from Northwestern University & an undergraduate degree in Political Science from the University of Chicago.
Metis (https://thisismetis.com/) accelerates data science learning for individuals, companies, & institutions through corporate training & accredited, immersive bootcamps.
The Metis bootcamp curriculum is designed & delivered by highly educated & industry-experienced practitioners, & all bootcamp graduates receive hands-on career support until theyre hired. Campuses are located in Chicago, New York City, San Francisco, & Live Online.
On the corporate side, Metis works with large organizations who want to upskill their teams in data science & analytics to gain efficiencies, remain competitive, & improve their bottom lines. Metis is proud to be backed by Kaplan, a global leader in education.
Join our Metis Community Slack channel!
Apply here: http://bit.ly/MetisCommunitySlack
Metis Code of Conduct
Metis is dedicated to providing a harassment-free experience for everyone, regardless of gender identity, age, sexual orientation, disability, physical appearance, body size, race, or religion (or lack thereof).
We do not tolerate harassment of students, staff, or visitors in any form. Sexual language & imagery is not appropriate for any event including talks, workshops, parties, & other online media. Individuals & groups that do not abide by these rules will be asked to leave and, if necessary, prohibited from future events.
If you have any questions or you're made to feel uncomfortable by anyone on our campus or at one of our offsite events, please let one of the staff members know right away. The matter will be taken seriously & promptly addressed.