AdaShift: Learning Discriminative Self-Gated Neural Feature Activation With an Adaptive Shift Factor

S Cai - Proceedings of the IEEE/CVF Conference on …, 2024 - openaccess.thecvf.com
Nonlinearities are decisive in neural representation learning. Traditional Activation (Act)
functions impose fixed inductive biases on neural networks with oriented biological …

Three-dimensional hybrid fusion networks for current-based bearing fault diagnosis

X Huang, T **e, J Hu, Q Zhou - Measurement Science and …, 2023 - iopscience.iop.org
Intelligent fault diagnosis (IFD) techniques commonly use vibration-based measurements to
perform health monitoring of critical rotating components in industrial systems. However …

[HTML][HTML] How Resilient Are Kolmogorov–Arnold Networks in Classification Tasks? A Robustness Investigation

ADM Ibrahum, Z Shang, JE Hong - Applied Sciences, 2024 - mdpi.com
Kolmogorov–Arnold Networks (KANs) are a novel class of neural network architectures
based on the Kolmogorov–Arnold representation theorem, which has demonstrated …

SchNet_IIA: Potential Energy Surface Fitting by Interatomic Interactions Attention Based on Transfer Learning Analysis

KL Jiang, HQ Wang, HF Li, SW Pan… - Journal of Chemical …, 2024 - ACS Publications
Machine learning methods for fitting potential energy surfaces and molecular dynamics
simulations are becoming increasingly popular due to their potentially high accuracy and …