Toward Knowledge Extraction in Classification of Volcano-Seismic Events: Visualizing Hidden States in Recurrent Neural Networks

Toward Knowledge Extraction in Classification of Volcano-Seismic Events: Visualizing Hidden States in Recurrent Neural Networks

Understanding how deep hierarchical models build their knowledge is a key issue in the usage of artificial intelligence to interpret the reality behind data. Depending on the discipline and models used, such knowledge may be represented in ways that are more or less intelligible for humans, limiting...

Full description

Bibliographic Details
Main Authors: Manuel Titos, Luz Garcia, Milad Kowsari, Carmen Benitez
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Knowledge based systems
learning (artificial intelligence)
supervised learning
machine learning
deep learning
representation learning
Online Access:https://ieeexplore.ieee.org/document/9726918/

Internet

https://ieeexplore.ieee.org/document/9726918/

Similar Items