Imposing Star-Shaped Hard Constraints on the Neural Network Output
A problem of imposing hard constraints on the neural network output can be met in many applications. We propose a new method for solving this problem for non-convex constraints that are star-shaped. A region produced by constraints is called star-shaped when there exists an origin in the region from...
Saved in:
| Main Authors: | Andrei Konstantinov, Lev Utkin, Vladimir Muliukha |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/12/23/3788 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
High-Accuracy Parallel Neural Networks with Hard Constraints for a Mixed Stokes/Darcy Model
by: Zhulian Lu, et al.
Published: (2025-03-01) -
Stochastic orderings induced by star-shaped functions
by: Henry A. Krieger
Published: (1991-01-01) -
Topology-Dependent Antifreeze Properties of Biomimetic Linear and Star-Shaped Peptoids
by: Lei Feng, et al.
Published: (2025-06-01) -
Leveraging petrophysical and geological constraints for AI-driven predictions of total organic carbon (TOC) and hardness in unconventional reservoir prospects
by: Nandito Davy, et al.
Published: (2024-12-01) -
Accurate scoliosis vertebral landmark localization on X-ray images via shape-constrained multi-stage cascaded CNNs
by: Zhiwei Wang, et al.
Published: (2024-11-01)