Hyper-flexible convolutional neural networks based on generalized Lehmer and power means

DOI10.1016/J.NEUNET.2022.08.017WikidataQ116846987 ScholiaQ116846987MaRDI QIDQ6488726

Vladyslav Branytskyi, Mariia Golovianko, Vagan Terziyan, Diana Malyk

Publication date: 18 October 2023

Published in: Neural Networks (Search for Journal in Brave)

zbMATH Keywords

poolingflexibilityLehmer meanpower meanconvolutional neural networkadversarial robustness

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Weak monotonicity of Lehmer and Gini means
• Power Function Error Initialization Can Improve Convergence of Backpropagation Learning in Neural Networks for Classification
• Multibranch Formal Neuron: An Internally Nonlinear Learning Unit
• Flexible Transmitter Network
• A Correspondence Between Normalization Strategies in Artificial and Biological Neural Networks
• On PDE Characterization of Smooth Hierarchical Functions Computed by Neural Networks
• Simple Convolutional-Based Models: Are They Learning the Task or the Data?
• The unreasonable effectiveness of deep learning in artificial intelligence
• Minimal Spiking Neuron for Solving Multilabel Classification Tasks
• Integration of Stochastic Models by Minimizing α-Divergence

This page was built for publication: Hyper-flexible convolutional neural networks based on generalized Lehmer and power means