Institutional Scholarship

Auditing Deep Neural Networks and Other Black-box Models

Show simple item record

dc.contributor.advisor Friedler, Sorelle
dc.contributor.author Falk, Casey
dc.date.accessioned 2016-07-18T11:21:40Z
dc.date.available 2016-07-18T11:21:40Z
dc.date.issued 2016
dc.identifier.uri http://hdl.handle.net/10066/18664
dc.description.abstract In this era of self-driving cars, smart watches, and voice-commanded speakers, machine learning is ubiquitous. Recently, deep learning has shown impressive success in solving many machine learning problems related to image data and sequential data - with the result that people are frequently impacted by deep learning models on a daily basis. However, how do we judge if these models are fair, and how do we discover what information is important when making a decision? And as APIs become ever-more common, how do we determine this information if we do not have access to the model itself? We developed a novel technique called Gradient Feature Auditing which gradually obscures information from a data-set and evaluates how a model's predictions change as yet more of that information is obscured. This allows a deeper investigation of what information and features are actually used by machine learning models when making predictions. Throughout our experiments, we apply Gradient Feature Auditing on multiple data-sets using several popular modeling techniques (linear SVMs, C4.5 decision trees, and shallow feed-forward neural networks) to provide evidence that Gradient Feature Auditing indeed affords deeper insight into what information a model is using.
dc.description.sponsorship Haverford College. Department of Computer Science
dc.language.iso eng
dc.rights.uri http://creativecommons.org/licenses/by-nc/4.0/
dc.title Auditing Deep Neural Networks and Other Black-box Models
dc.type Thesis
dc.rights.access Open Access


Files in this item

This item appears in the following Collection(s)

Show simple item record

http://creativecommons.org/licenses/by-nc/4.0/ Except where otherwise noted, this item's license is described as http://creativecommons.org/licenses/by-nc/4.0/

Search


Browse

My Account