IEEE Signal Processing Magazine· 2017Q1· Review
Geometric Deep Learning: Going beyond Euclidean data
- 3,646citations
- Q1SCImago
- 2017year
Short summary
Geometric deep learning (GDL) extends deep neural networks to non-Euclidean data like graphs and manifolds, enabling analysis of complex, structured information.
AI-generated from the title and abstract; the full text is not read.
Key points
- Deep learning models are being generalized to non-Euclidean domains like graphs and manifolds.
- This field, termed Geometric Deep Learning (GDL), addresses data structures beyond simple grids.
- The paper provides an overview of GDL problems, solutions, and applications.
- Key difficulties and future research avenues in GDL are discussed.
AI-generated from the title and abstract; the full text is not read.
Abstract
Geometric deep learning is an umbrella term for emerging techniques attempting to generalize (structured) deep neural models to non-Euclidean domains, such as graphs and manifolds. The purpose of this article is to overview different examples of geometric deep-learning problems and present available solutions, key difficulties, applications, and future research directions in this nascent field.
The authors' abstract, as published at the source. IEEE Signal Processing Magazine, 2017 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Computational Mechanics
Computational MechanicsEngineering