Kolmogorov GAM Networks Are All You Need!
Kolmogorov GAM (K-GAM) networks have been shown to be an efficient architecture for both training and inference. They are additive models with embeddings that are independent of the target function of interest. They provide an alternative to Transformer architectures. They are the machine learning v...
Saved in:
Main Authors: | Sarah Polson, Vadim Sokolov |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2025-05-01
|
Series: | Entropy |
Subjects: | |
Online Access: | https://www.mdpi.com/1099-4300/27/6/593 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
VeinKAN: A Finger Vein Recognition Model Based on Kolmogorov–Arnold Networks
by: Tran An Cong, et al.
Published: (2025-01-01) -
Hybrid Transformer-KAN Within Federated Learning Framework: A Novel Machine Learning Approach for Improved Short-Term Weather Forecasting
by: Shuai Jin, et al.
Published: (2025-01-01) -
Kolmogorov–Arnold–Enhanced Nonlinear Expansions for Fine-Grained Feature Amplification in Robust Near-Shore SAR Vessel Discrimination
by: Hankang Wang, et al.
Published: (2025-01-01) -
Enhancing FT-Transformer With a Matérn-Driven Kolmogorov-Arnold Feature Tokenizer for Tabular Data-Based In-Bed Posture Classification
by: Bing Zhou, et al.
Published: (2025-01-01) -
Cheby-KANs: Advanced Kolmogorov–Arnold Networks for Applying Geometric Deep Learning in Quantum Chemistry Applications
by: Amgad Abdallah Mahmoud, et al.
Published: (2025-01-01)