Neumann, M;
Stenetorp, P;
Riedel, S;
(2016)
Learning to Reason with Adaptive Computation.
In:
Interpretable Machine Learning for Complex Systems: NIPS 2016 workshop proceedings.
NIPS 2016: Barcelona, Spain.
Preview |
Text
1610.07647.pdf - Published Version Download (412kB) | Preview |
Abstract
Multi-hop inference is necessary for machine learning systems to successfully solve tasks such as Recognising Textual Entailment and Machine Reading. In this work, we demonstrate the effectiveness of adaptive computation for learning the number of inference steps required for examples of different complexity and that learning the correct number of inference steps is difficult. We introduce the first model involving Adaptive Computation Time which provides a small performance benefit on top of a similar model without an adaptive component as well as enabling considerable insight into the reasoning process of the model.
| Type: | Proceedings paper |
|---|---|
| Title: | Learning to Reason with Adaptive Computation |
| Event: | Interpretable Machine Learning for Complex Systems: NIPS 2016 workshop |
| Location: | Barcelona, Spain |
| Dates: | 09 December 2016 - 09 December 2016 |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://sites.google.com/site/nips2016interpretml/... |
| Language: | English |
| Additional information: | Copyright © The Authors 2016. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/1530879 |
Archive Staff Only
 |
View Item |
