User Tools

Site Tools


projects:year8:8a.004.uva

This is an old revision of the document!


8a.004.UVA - General Techniques for Explaining/Interpreting Deep Neural Networks

Project - Summary

  • Much of the recent advancement in machine learning has been through neural networks (NNs), and in particular deep learning (DL) has shown record-breaking performance across many domains
  • In some fields where there is a human element involved, e.g. in medicine and finance, there can be legal or ethical considerations that require decisions to be interpretable/explainable. This requirement often prohibits the use of NNs and other so-called 'black-box' models.
  • There have been some proposed techniques to help explain the internal workings of NNs, many focused on image/visual recognition.
  • One of these methods known as feature occlusion shows promise for non-image and multi-modal data.
  • We propose to investigate the use of feature occlusion and potentially develop other techniques for use as general methods for explaining and interpreting deep learning models.

Project - Team

Team Member Role Email Phone Number Academic Site/IAB
Peter Beling PI pb3a@virginia.edu University of Virginia
Stephen Adams Research Scientist University of Virginia
Alex Langevin Student University of Virginia
Funded by: U-ANGEL

Project - Novelty of Approach

This project seeks to determine the feasibility and performance of feature occlusion and other techniques as general methods of explainable AI with test case implementation in IAB member defined settings

Project - Deliverables

Deliverables
1 Briefing of model design
2 Literature review document
3 Software and associated artifacts
4 Final report

Project - Benefits to IAB

  1. Improved model accuracy while maintaining interpretability
  2. Ability to explain model results where legally or ethically required
  3. In commercial or engineering settings, improved business intelligence and diagnostic data gathering

Project - Documents

FilenameFilesizeLast modified
8a.004.uva_final_report.docx599.7 KiB2020/10/31 11:16
8a.004.uva_year_8_project_proposal_revised_09.27.2019.docx54.1 KiB2019/09/27 11:38
8a.004.uva_explainable_ai_year_8_quad_chart_beling.pptx59.5 KiB2019/09/25 17:12
projects/year8/8a.004.uva.1569449440.txt.gz · Last modified: 2019/09/25 17:10 by sally.johnson