English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recurrent neural networks, and in particular long short-term memory (LSTM)networks, are a remarkably effective tool for sequence modeling that learn adense black-box hidden representation of their sequential input. Researchersinterested in better understanding these models have studied the changes inhidden state representations over time and noticed some interpretable patternsbut also significant noise. In this work, we present LSTMVIS, a visual analysistool for recurrent neural networks with a focus on understanding these hiddenstate dynamics. The tool allows users to select a hypothesis input range tofocus on local state changes, to match these states changes to similar patternsin a large data set, and to align these results with structural annotationsfrom their domain. We show several use cases of the tool for analyzing specifichidden state properties on dataset containing nesting, phrase structure, andchord progressions, and demonstrate how the tool can be used to isolatepatterns for further statistical analysis. We characterize the domain, thedifferent stakeholders, and their goals and tasks.

LSTMVis: A Tool for Visual Analysis of Hidden State Dynamics in Recurrent Neural Networks