Decoder Choice Network for Metalearning

Jialin Liu, Fei Chao, Longzhi Yang, Chih Min Lin, Changjing Shang, Qiang Shen

Allbwn ymchwil: Cyfraniad at gyfnodolynErthygladolygiad gan gymheiriaid

3 Dyfyniadau(SciVal)
41 Wedi eu Llwytho i Lawr (Pure)


Metalearning has been widely applied for implementing few-shot learning and fast model adaptation. Particularly, existing metalearning methods have been exploited to learn the control mechanism for gradient descent processes, in an effort to facilitate gradient-based learning in gaining high speed and generalization ability. This article presents a novel method that controls the gradient descent process of the model parameters in a neural network, by limiting the model parameters within a low-dimensional latent space. The main challenge for implementing this idea is that a decoder with many parameters may be required. To tackle this problem, the article provides an alternative design of the decoder with a structure that shares certain weights, thereby reducing the number of required parameters. In addition, this work combines ensemble learning with the proposed approach to improve the overall learning performance. Systematic experimental studies demonstrate that the proposed approach offers results superior to the state of the art in performing the Omniglot classification and miniImageNet classification tasks.
Iaith wreiddiolSaesneg
Tudalennau (o-i)3440-3453
Nifer y tudalennau14
CyfnodolynIEEE Transactions on Cybernetics
Rhif cyhoeddi6
Dyddiad ar-lein cynnar01 Rhag 2021
Dynodwyr Gwrthrych Digidol (DOIs)
StatwsCyhoeddwyd - 01 Meh 2023

Ôl bys

Gweld gwybodaeth am bynciau ymchwil 'Decoder Choice Network for Metalearning'. Gyda’i gilydd, maen nhw’n ffurfio ôl bys unigryw.

Dyfynnu hyn