arrow
返回

Balance gate controlled deep neural network

delete2018-12-01
delete18
PRE
AI
A
Anji Liu
Y
Yuanjun Laili *
DOI:10.1016/j.neucom.2018.08.075delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
By mimicking the information expression ways in human's brain, deep neural network refers to a deeply structured framework with multiple processing layers that attempt to model high-level abstractions of the data. It is becoming a mainstream technology for pattern recognition, data mining and intelligent control at industrial scale. Previous work on constructing very deep networks, such as convolutional neural network and recurrent neural network, makes complex tasks such as image classification feasible. However, they are very limited when dealing with irregular data whose features are unstructured or even unknown. The traditional fully connected neural network is contrarily too shallow to extract high-level features. In this paper, we present a balance gate controlled deep network structure to deepen the fully connected neural network. It uses a new gating strategy to control information flow and increase network stability. Experimental results on both irregular regression and time-series forecasting demonstrate that the proposed network out-performs other ad-hoc models and is easier to train in a deeper form than the fully connected neural network. (C) 2018 Elsevier B.V. All rights reserved.
Keyword:
Deep neural network
Balanced gate
Light-weight training
Regression
Time-series prediction
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Neurocomputing 封面图
Neurocomputing
IF:
6.5
论文数:
2.5W
被引数:
6.5W

机构

B
Beihang University
学者数:
5.2W
论文数: 4.1W
被引数: 37
引用论文

引用论文

Prognostic role of FUT8 expression in relation to p53 status in stage II and III colorectal cancer
err2018-07-05
err0
errOAAI
errMasaru Noda; Hirokazu Okayama; Yasuhide Kofunato; Shun Chida; Katsuharu Saito; Takeshi Tada; Mai Ashizawa; Takahiro Nakajima; Keita Aoto; Tomohiro Kikuchi; Wataru Sakamoto; Hisahito Endo; Shotaro Fujita; Motonobu Saito; Tomoyuki Momma; Shinji Ohki; Koji Kono
err分享
err收藏
Checkerboard Self-Patterning of an Ionic Liquid Film on Mercury
err2011-05-10
err0
errOAAI
errL. Tamam; B. M. Ocko; H. Reichert; M. Deutsch
err分享
err收藏
Accurate seat belt detection in road surveillance images based on CNN and SVM
err2018-01-01
err31
errOAAI
errChen, Yanxiang; Tao, Gang; Ren, Hongmei; Lin, Xinyu; Zhang, Luming
err分享
err收藏
Friction Models and Friction Compensation摩擦模型与摩擦补偿
err1998-01-01
err0
PREAI
errH. Olsson; K.J. Åström; C. Canudas de Wit; M. Gäfvert; P. Lischinsky
err分享
err收藏
A fast learning algorithm for evolving neo-fuzzy neuron
err2014-01-01
err73
PREAI
errSilva, Alisson Marques; Caminhas, Walmir; Lemos, Andre; Gomide, Fernando
err分享
err收藏
err分享
err收藏
Multivariable Gaussian Evolving Fuzzy Modeling System
err2011-02-01
err154
PREAI
errLemos, Andre; Caminhas, Walmir; Gomide, Fernando
err分享
err收藏
学者 查看更多内容