Deep Neural Networks With Trainable Activations and Controlled Lipschitz Constant

DOI10.1109/TSP.2020.3014611MaRDI QIDQ5103019zbMATH OpenOpenAlexFDO

Authors Shayan Aziznejad, Harshit Gupta, Joaquim Campos, M. Unser

Publication date 23 September 2022

Published in IEEE Transactions on Signal Processing (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2001.06263

Mathematics Subject Classification ID

Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Cited in

(8)

• Lipschitz Certificates for Layered Network Structures Driven by Averaged Activation Operators
• A survey on modern trainable activation functions
• CLIP: cheap Lipschitz training of neural networks
• Linear inverse problems with Hessian-Schatten total variation
• Approximation of Lipschitz Functions Using Deep Spline Neural Networks
• Sparsest piecewise-linear regression of one-dimensional data
• On Lipschitz Bounds of General Convolutional Neural Networks
• What Kinds of Functions Do Deep Neural Networks Learn? Insights from Variational Spline Theory

This page was built for publication: Deep Neural Networks With Trainable Activations and Controlled Lipschitz Constant

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5103019)