Subset Sampling for Progressive Neural Network Learning

Tutkimustuotos: KonferenssiartikkeliScientificvertaisarvioitu

Abstrakti

Progressive Neural Network Learning is a class of algorithms that incrementally construct the network's topology and optimize its parameters based on the training data. While this approach exempts the users from the manual task of designing and validating multiple network topologies, it often requires an enormous number of computations. In this paper, we propose to speed up this process by exploiting subsets of training data at each incremental training step. Three different sampling strategies for selecting the training samples according to different criteria are proposed and evaluated. We also propose to perform online hyperparameter selection during the network progression, which further reduces the overall training time. Experimental results in object, scene and face recognition problems demonstrate that the proposed approach speeds up the optimization procedure considerably while operating on par with the baseline approach exploiting the entire training set throughout the training process.

AlkuperäiskieliEnglanti
Otsikko2020 IEEE International Conference on Image Processing, ICIP 2020 - Proceedings
KustantajaIEEE
Sivut713-717
Sivumäärä5
ISBN (elektroninen)9781728163956
DOI - pysyväislinkit
TilaJulkaistu - lokak. 2020
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaIEEE International Conference on Image Processing - Virtual, Abu Dhabi, Yhdistyneet arabiemiirikunnat
Kesto: 25 syysk. 202028 syysk. 2020

Julkaisusarja

NimiProceedings - International Conference on Image Processing, ICIP
Vuosikerta2020-October
ISSN (painettu)1522-4880

Conference

ConferenceIEEE International Conference on Image Processing
Maa/AlueYhdistyneet arabiemiirikunnat
KaupunkiVirtual, Abu Dhabi
Ajanjakso25/09/2028/09/20

Julkaisufoorumi-taso

  • Jufo-taso 1

!!ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Sormenjälki

Sukella tutkimusaiheisiin 'Subset Sampling for Progressive Neural Network Learning'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä