Deep Neural Networks With Trainable Activations and Controlled Lipschitz Constant

DOI10.1109/TSP.2020.3014611OpenAlexW3048660463MaRDI QIDQ5103019FDOQ5103019

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)

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

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)