Three Decades of Activations: A Comprehensive Survey of 400 Activation Functions for Neural Networks
V Kunc, J Kléma - arXiv preprint arXiv:2402.09092, 2024 - arxiv.org
Neural networks have proven to be a highly effective tool for solving complex problems in
many areas of life. Recently, their importance and practical usability have further been …
many areas of life. Recently, their importance and practical usability have further been …
Adaptive activation functions for predictive modeling with sparse experimental data
F Pourkamali-Anaraki, T Nasrin, RE Jensen… - Neural Computing and …, 2024 - Springer
A pivotal aspect in the design of neural networks lies in selecting activation functions, crucial
for introducing nonlinear structures that capture intricate input–output patterns. While the …
for introducing nonlinear structures that capture intricate input–output patterns. While the …
Deep learning-based prediction of initiation jet momentum ratio in jet-induced oblique detonations
Y Bao, R Qiu, J Lou, X Han, Y You - Aerospace Science and Technology, 2024 - Elsevier
Oblique detonation, with its attributes of self-ignition, rapid heat release, and high thermal
cycle efficiency, has garnered significant attention. It is crucial to explore methods that …
cycle efficiency, has garnered significant attention. It is crucial to explore methods that …
[HTML][HTML] Adaptive Morphing Activation Function for Neural Networks
O Herrera-Alcántara, S Arellano-Balderas - Fractal and Fractional, 2024 - mdpi.com
A novel morphing activation function is proposed, motivated by the wavelet theory and the
use of wavelets as activation functions. Morphing refers to the gradual change of shape to …
use of wavelets as activation functions. Morphing refers to the gradual change of shape to …