Результаты исследований: Публикации в книгах, отчётах, сборниках, трудах конференций › статья в сборнике материалов конференции › научная › Рецензирование
Simultaneous Perturbation Stochastic Approximation for Few-Shot Learning. / Boiarov, Andrei; Granichin, Oleg; Granichina, Olga.
European Control Conference 2020, ECC 2020. Institute of Electrical and Electronics Engineers Inc., 2020. стр. 350-355 9143831 (European Control Conference 2020, ECC 2020).Результаты исследований: Публикации в книгах, отчётах, сборниках, трудах конференций › статья в сборнике материалов конференции › научная › Рецензирование
}
TY - GEN
T1 - Simultaneous Perturbation Stochastic Approximation for Few-Shot Learning
AU - Boiarov, Andrei
AU - Granichin, Oleg
AU - Granichina, Olga
PY - 2020/5
Y1 - 2020/5
N2 - Few-shot learning is an important research field of machine learning in which a classifier must be trained in such a way that it can adapt to new classes which are not included in the training set. However, only small amounts of examples of each class are available for training. This is one of the key problems with learning algorithms of this type which leads to the significant uncertainty. We attack this problem via randomized stochastic approximation. In this paper, we suggest to consider the new multi-task loss function and propose the SPSA-like few-shot learning approach based on the prototypical networks method. We provide a theoretical justification and an analysis of experiments for this approach. The results of experiments on the benchmark dataset demonstrate that the proposed method is superior to the original prototypical networks.
AB - Few-shot learning is an important research field of machine learning in which a classifier must be trained in such a way that it can adapt to new classes which are not included in the training set. However, only small amounts of examples of each class are available for training. This is one of the key problems with learning algorithms of this type which leads to the significant uncertainty. We attack this problem via randomized stochastic approximation. In this paper, we suggest to consider the new multi-task loss function and propose the SPSA-like few-shot learning approach based on the prototypical networks method. We provide a theoretical justification and an analysis of experiments for this approach. The results of experiments on the benchmark dataset demonstrate that the proposed method is superior to the original prototypical networks.
UR - http://www.scopus.com/inward/record.url?scp=85090126401&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85090126401
SN - 9783907144015
T3 - European Control Conference 2020, ECC 2020
SP - 350
EP - 355
BT - European Control Conference 2020, ECC 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 19th European Control Conference, ECC 2020
Y2 - 12 May 2020 through 15 May 2020
ER -
ID: 62141876