University of Cambridge > Talks.cam > CUED Computer Vision Research Seminars > Visualizing and Understanding Recurrent Networks

Visualizing and Understanding Recurrent Networks

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact rff22.

Any further queries regarding meeting, please direct them to Ankur Handa ah781@cam.ac.uk

Recurrent Neural Networks (RNNs), and specifically a variant with Long Short-Term Memory (LSTM), are enjoying renewed interest as a result of successful applications in a wide range of machine learning problems that involve sequential data. However, while LST Ms provide exceptional results in practice, the source of their performance and their limitations remain rather poorly understood. Using character-level language models as an interpretable testbed, we aim to bridge this gap by providing a comprehensive analysis of their representations, predictions and error types. In particular, our experiments reveal the existence of interpretable cells that keep track of long-range dependencies such as line lengths, quotes and brackets. Moreover, an extensive analysis with finite horizon n-gram models suggest that these dependencies are actively discovered and utilized by the networks. Finally, we provide detailed error analysis that suggests areas for further study.

This talk is part of the CUED Computer Vision Research Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity