LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 1 of total 1

Search options

Article ; Online: Long short-term memory with activation on gradient.

Qin, Chuan / Chen, Liangming / Cai, Zangtai / Liu, Mei / Jin, Long

Neural networks : the official journal of the International Neural Network Society

2023  Volume 164, Page(s) 135–145

Abstract: As the number of long short-term memory (LSTM) layers increases, vanishing/exploding gradient problems exacerbate and have a negative impact on the performance of the LSTM. In addition, the ill-conditioned problem occurs in the training process of LSTM ... ...

Abstract As the number of long short-term memory (LSTM) layers increases, vanishing/exploding gradient problems exacerbate and have a negative impact on the performance of the LSTM. In addition, the ill-conditioned problem occurs in the training process of LSTM and adversely affects its convergence. In this work, a simple and effective method of the gradient activation is applied to the LSTM, while empirical criteria for choosing gradient activation hyperparameters are found. Activating the gradient refers to modifying the gradient with a specific function named the gradient activation function. Moreover, different activation functions and different gradient operations are compared to prove that the gradient activation is effective on LSTM. Furthermore, comparative experiments are conducted, and their results show that the gradient activation alleviates the above problems and accelerates the convergence of the LSTM. The source code is publicly available at https://github.com/LongJin-lab/ACT-In-NLP.
MeSH term(s) Neural Networks, Computer ; Memory, Short-Term ; Memory, Long-Term ; Software
Language English
Publishing date 2023-04-25
Publishing country United States
Document type Journal Article
ZDB-ID 740542-x
ISSN 1879-2782 ; 0893-6080
ISSN (online) 1879-2782
ISSN 0893-6080
DOI 10.1016/j.neunet.2023.04.026
Shelf mark
Zs.A 2365: Show issues Location:
Je nach Verfügbarkeit (siehe Angabe bei Bestand)
bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular
Jg. 1995 - 2021: Lesesall (2.OG)
ab Jg. 2022: Lesesaal (EG)
Database MEDical Literature Analysis and Retrieval System OnLINE

More links

Kategorien

To top