Auditing Deep Neural Networks and Other Black-box Models

Simple item page
dc.contributor.advisorFriedler, Sorelle
dc.contributor.authorFalk, Casey
dc.date.accessioned2016-07-18T11:21:40Z
dc.date.available2016-07-18T11:21:40Z
dc.date.issued2016
dc.description.abstractIn 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.sponsorshipHaverford College. Department of Computer Science
dc.identifier.urihttp://hdl.handle.net/10066/18664
dc.language.isoeng
dc.rights.accessOpen Access
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/
dc.titleAuditing Deep Neural Networks and Other Black-box Models
dc.typeThesis
Files
Original bundle
Now showing 1 - 2 of 2
Thumbnail Image
Name:
2016FalkC.pdf
Size:
10 MB
Format:
Adobe Portable Document Format
Description:
Thesis
Download
Thumbnail Image
Name:
2016FalkC_release.pdf
Size:
364.51 KB
Format:
Adobe Portable Document Format
Description:
Archive Staff only
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Computer Science