A Variational Inequality Model for Learning Neural Networks

Neural networks have become ubiquitous tools for solving signal and image processing problems, and they often outperform standard approaches. Nevertheless, training the layers of a neural network is a challenging task in many applications. The prevalent training procedure consists of minimizing high...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) s. 1 - 5
Hlavní autoři: Combettes, Patrick L., Pesquet, Jean-Christophe, Repetti, Audrey
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 04.06.2023
Témata:
Block-iterative algorithm
MRI
Neural networks
Numerical models
Signal processing
Signal processing algorithms
Task analysis
Training
Transfer learning
variational inequality
ISSN:2379-190X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Neural networks have become ubiquitous tools for solving signal and image processing problems, and they often outperform standard approaches. Nevertheless, training the layers of a neural network is a challenging task in many applications. The prevalent training procedure consists of minimizing highly non-convex objectives based on data sets of huge dimension. In this context, current methodologies are not guaranteed to produce global solutions. We present an alternative approach which foregoes the optimization framework and adopts a variational inequality formalism. The associated algorithm guarantees convergence of the iterates to a true solution of the variational inequality and it possesses an efficient block-iterative structure. A numerical application is presented.
ISSN:2379-190X
DOI:10.1109/ICASSP49357.2023.10095688