Decontextualized learning for interpretable hierarchical representations of visual patterns

Decontextualized learning for interpretable hierarchical representations of visual patterns

Summary: Apart from discriminative modeling, the application of deep convolutional neural networks to basic research utilizing natural imaging data faces unique hurdles. Here, we present decontextualized hierarchical representation learning (DHRL), designed specifically to overcome these limitations...

Full description

Bibliographic Details
Main Authors: Robert Ian Etheredge, Manfred Schartl, Alex Jordan
Format: Article
Language:English
Published: Elsevier 2021-02-01
Series:Patterns
Subjects:
generative modeling
interpretable AI
disentangled representation learning
hierarchical features
image analysis
small data
Online Access:http://www.sciencedirect.com/science/article/pii/S2666389920302634

Internet

http://www.sciencedirect.com/science/article/pii/S2666389920302634

Similar Items