Data

Tools

Indexes

Applications

Experiments

Repos

An open API service providing repository metadata for many open source software ecosystems.

GitHub / cslab-hub / GlobalTimeSeriesCoherenceMatrices

Code for the Paper Constructing Global Coherence Representations:Identifying Interpretability and Coherences ofTransformer Attention in Time Series Data. It is about creating coherence matrices which represent the attention from each symbol to each other symbol.

JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cslab-hub%2FGlobalTimeSeriesCoherenceMatrices

Stars: 1
Forks: 0
Open issues: 0

License: mit
Language: TypeScript
Size: 114 MB
Dependencies parsed at: Pending

Created at: almost 4 years ago
Updated at: about 2 years ago
Pushed at: over 3 years ago
Last synced at: 3 months ago

Topics: attention, deep-learning, tensorflow, time-series-analysis, transformer-encoder, xai

    Loading...