Neither Quick Nor Proper--Evaluation of QuickProp for Learning Deep Neural Networks

Long short-term memory with activation on gradient

C Qin, L Chen, Z Cai, M Liu, L Jin - Neural Networks, 2023 - Elsevier
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 …
被引用次数：10 相关文章 所有 5 个版本
[PDF] neurips.cc

Parabolic approximation line search for dnns

M Mutschler, A Zell - Advances in neural information …, 2020 - proceedings.neurips.cc
A major challenge in current optimization research for deep learning is to automatically find
optimal step sizes for each update step. The optimal step size is closely related to the shape …
被引用次数：16 相关文章 所有 10 个版本

Разработка и исследование метода двухэтапного распознавания графических примитивов

ГА Чистяков, ОК Эсаулов - 2019 - elibrary.ru
Предлагается метод двухэтапного распознавания графических примитивов в
видеопотоке, базирующийся на идее совместного использования независимых …
相关文章

[引用][C] An Advanced machine learning approach to estimate the state of charge of battery energy storage system for micro-grid

JMDS Jeewandara - 2021
相关文章

[引用][C] Parabolic Approximation Line Search: An efficient and effective line search approach for DNNs

M Mutschler, A Zell
相关文章

[引用][C] PAL: A fast DNN optimization method based on curvature information.

M Mutschler, A Zell - arXiv preprint arXiv:1903.11991, 2019
相关文章