Feedforward neural networks initialization based on discriminant learning

Tutkimustuotos: ArtikkeliScientificvertaisarvioitu

3 Lataukset (Pure)

Abstrakti

In this paper, a novel data-driven method for weight initialization of Multilayer Perceptrons and Convolutional 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.

AlkuperäiskieliEnglanti
Sivut220-229
Sivumäärä10
JulkaisuNeural Networks
Vuosikerta146
Varhainen verkossa julkaisun päivämäärä25 marrask. 2021
DOI - pysyväislinkit
TilaJulkaistu - helmik. 2022
OKM-julkaisutyyppiA1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä

Julkaisufoorumi-taso

  • Jufo-taso 2

!!ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Artificial Intelligence

Sormenjälki

Sukella tutkimusaiheisiin 'Feedforward neural networks initialization based on discriminant learning'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä