Planned intervention: On Wednesday April 3rd 05:30 UTC Zenodo will be unavailable for up to 2-10 minutes to perform a storage cluster upgrade.
Published November 25, 2021 | Version v1
Journal article Open

Feedforward neural networks initialization based on discriminant learning

  • 1. Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland
  • 2. Department of Electrical and Computer Engineering, Aarhus University, Aarhus, Denmark

Description

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.

Notes

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

WeightsInitialization_NN_2022.pdf

Files (1.7 MB)

Name Size Download all
md5:f34bca2a2035fe9ec3258d573caf7219
1.7 MB Preview Download

Additional details

Related works

Funding

MARVEL – Multimodal Extreme Scale Data Analytics for Smart Cities Environments 957337
European Commission