Efficient and sparse neural networks by pruning weights in a multiobjective learning approach
Year of publication: |
2022
|
---|---|
Authors: | Reiners, Malena ; Klamroth, Kathrin ; Heldmann, Fabian ; Stiglmayr, Michael |
Published in: |
Computers & operations research : and their applications to problems of world concern ; an international journal. - Oxford [u.a.] : Elsevier, ISSN 0305-0548, ZDB-ID 194012-0. - Vol. 141.2022, p. 1-16
|
Subject: | -regularization | Automated machine learning | Multiobjective learning | Stochastic multi-gradient descent | Unstructured pruning | Neuronale Netze | Neural networks | Künstliche Intelligenz | Artificial intelligence | Theorie | Theory | Lernprozess | Learning process | Multikriterielle Entscheidungsanalyse | Multi-criteria analysis | Lernen | Learning | Mathematische Optimierung | Mathematical programming | Prognoseverfahren | Forecasting model |
-
Deep learning, predictability, and optimal portfolio returns
Babiak, Mykola, (2020)
-
Visual saliency modeling with deep learning : a comprehensive review
Abraham, Shilpa Elsa, (2023)
-
Predictive market making via machine learning
Haider, Abbas, (2022)
- More ...
-
Ordinal optimization through multi-objective reformulation
Klamroth, Kathrin, (2023)
-
On the multicriteria allocation problem
Stiglmayr, Michael, (2014)
-
Representation of the non-dominated set in biobjective discrete optimization
Vaz, Daniel, (2015)
- More ...