Journal article Open Access

Feedforward neural networks initialization based on discriminant learning

Kateryna Chumachenko; Alexandros Iosifidis; Moncef Gabbouj

In this paper, a novel data-driven method for weight initialization of Multilayer Perceptrons andConvolutional Neural Networks based on discriminant learning is proposed. The approach relaxes some of the limitations of competing data-driven methods, including unimodality assumptions, limitations on the architectures related to limited maximal dimensionalities of the corresponding projection spaces, as well as limitations related to high computational requirements due to the need of eigendecomposition on high-dimensional data. We also consider assumptions of the method on the data and propose a way to account for them in a form of a new normalization layer. The experiments on three large-scale image datasets show improved accuracy of the trained models compared to competing random-based and data-driven weight initialization methods, as well as better convergence properties in certain cases.

This work is supported by Business Finland under project 5GVertical Integrated Industry for Massive Automation (5G-VIIMA). A. Iosifidis acknowledges funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 957337 (MARVEL).
Files (1.7 MB)
Name Size
WeightsInitialization_NN_2022.pdf
md5:f34bca2a2035fe9ec3258d573caf7219
1.7 MB Download
120
72
views
downloads
Views 120
Downloads 72
Data volume 125.2 MB
Unique views 112
Unique downloads 69

Share

Cite as