Emmanuel M. Smith
Visualising state space representations of LSTM networks
Smith, Emmanuel M.; Smith, Jim; Legg, Phil; Francis, Simon
Authors
Jim Smith James.Smith@uwe.ac.uk
Professor in Interactive Artificial Intelligence
Professor Phil Legg Phil.Legg@uwe.ac.uk
Professor in Cyber Security
Simon Francis
Abstract
Long Short-Term Memory (LSTM) networks have proven to be one of the most effective models for making predictions on sequence-based tasks. These models work by capturing, remembering, and forgetting information relevant to their future predictions. The non-linear complexity of the mechanisms involved in this process means we currently lack tools for achieving interpretability. Ideally, we want these models to provide an explanation of why they make a particular prediction, given a specific input. Researchers have explored the idea of interpreting LSTMs in specific contexts such as natural language processing or classification, but they put minimal focus on approaches which are generalisable across different applications. To alleviate this, in this work, we demonstrate a method which enables the interpretation and comparison of LSTM states during time series predictions. We show that by reducing the dimensionality of network states one can scalably visualise patterns and explain model behaviours.
Citation
Smith, E. M., Smith, J., Legg, P., & Francis, S. Visualising state space representations of LSTM networks. Presented at Workshop on Visualization for AI Explainability, Berlin, Germany
Presentation Conference Type | Other |
---|---|
Conference Name | Workshop on Visualization for AI Explainability |
Conference Location | Berlin, Germany |
Acceptance Date | Aug 2, 2018 |
Deposit Date | Sep 19, 2018 |
Publicly Available Date | Sep 19, 2018 |
Peer Reviewed | Not Peer Reviewed |
Public URL | https://uwe-repository.worktribe.com/output/863245 |
Additional Information | Title of Conference or Conference Proceedings : Workshop on Visualization for AI Explainability |
Files
visualising_networks.html
(1.5 Mb)
Other
You might also like
Disclosure control issues in complex medical data
(2023)
Presentation / Conference
SACRO: Semi-Automated Checking Of Research Outputs
(2023)
Presentation / Conference
A novel mirror neuron inspired decision-making architecture for human–robot interaction
(2023)
Journal Article
Downloadable Citations
About UWE Bristol Research Repository
Administrator e-mail: repository@uwe.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2024
Advanced Search