Источник
IEEE Journal of Selected Topics in Signal Processing
Дата публикации
26.09.2024
Авторы
Anh-Huy Phan
Andrzej Cichocki
Дмитрий Ермилов
Николай Козырский
Игорь Ворона
Константин Соболев
Поделиться
How to Train Your Unstable Looped Tensor Network
Deep Neural Networks,
Convolutional Neural Networks,
Tensor Decomposition,
Tensor Chain,
Tensor Train,
Tensor Networks,
Stability,
Sensitivity,
NN Compression,
Numerical Stability
Аннотация
This paper addresses a substantial question of how to compress Deep Neural Networks with convolutional kernels modeled as looped tensor networks or Tensor Chain (TC) while it is known that such tensor network (TN) encounters severe numerical instability.We study the perturbation of this TN, provide an interpretation of instability in TC, propose novel methods to gain stability of the decomposition and keep the tensor network robust, and attain better approximation. Experimental results will confirm the superiority of the proposed methods in the compression of well-known convolutional neural networks, and TC decomposition under challenging scenarios.
Похожие публикации
Вы можете задать нам вопрос или предложить совместный проект в области ИИ
partner@airi.net
По вопросам научного
сотрудничества и партнерства
сотрудничества и партнерства
pr@airi.net
Для журналистов и СМИ