NeuroView-RNN: It's About Time

Cj Barberan, Sina Alemmohammad, Naiming Liu, Randall Balestriero, Richard Baraniuk

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Recurrent Neural Networks (RNNs) are important tools for processing sequential data such as time-series or video. Interpretability is defined as the ability to be understood by a person and is different from explainability, which is the ability to be explained in a mathematical formulation. A key interpretability issue with RNNs is that it is not clear how each hidden state per time step contributes to the decision-making process in a quantitative manner. We propose NeuroView-RNN as a family of new RNN architectures that explains how all the time steps are used for the decision-making process. Each member of the family is derived from a standard RNN architecture by concatenation of the hidden steps into a global linear classifier. The global linear classifier has all the hidden states as the input, so the weights of the classifier have a linear mapping to the hidden states. Hence, from the weights, NeuroView-RNN can quantify how important each time step is to a particular decision. As a bonus, NeuroView-RNN also offers higher accuracy in many cases compared to the RNNs and their variants. We showcase the benefits of NeuroView-RNN by evaluating on a multitude of diverse time-series datasets.

Original languageEnglish (US)
Title of host publicationProceedings of 2022 5th ACM Conference on Fairness, Accountability, and Transparency, FAccT 2022
PublisherAssociation for Computing Machinery
Pages1683-1697
Number of pages15
ISBN (Electronic)9781450393522
DOIs
StatePublished - Jun 21 2022
Event5th ACM Conference on Fairness, Accountability, and Transparency, FAccT 2022 - Virtual, Online, Korea, Republic of
Duration: Jun 21 2022Jun 24 2022

Publication series

NameACM International Conference Proceeding Series

Conference

Conference5th ACM Conference on Fairness, Accountability, and Transparency, FAccT 2022
Country/TerritoryKorea, Republic of
CityVirtual, Online
Period6/21/226/24/22

Keywords

  • Recurrent neural networks
  • interpretability
  • time series

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Fingerprint

Dive into the research topics of 'NeuroView-RNN: It's About Time'. Together they form a unique fingerprint.

Cite this