COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |
University of Cambridge > Talks.cam > CUED Computer Vision Research Seminars > Visualizing and Understanding Recurrent Networks
Visualizing and Understanding Recurrent NetworksAdd 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. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsAthena SWAN Cambridge SIAM Chapter Probability CaMedia Next Genration Biophysics; Friday 8th November 2019 Type the title of a new list hereOther talksPlanck Stars: theory and observations CANCELLED First year PhD student fieldwork seminar Internal Displacement in Cyprus and childhood: The view from genetic social psychology Computer vision techniques for measuring deformation |