[PDF][PDF] 卷积神经网络研究综述
周飞燕, 金林鹏, 董军 - 计算机学报, 2017 - cjc.ict.ac.cn
摘要作为一个十余年来快速发展的崭新领域, 深度学习受到了越来越多研究者的关注,
它在特征提取和模型拟合上都有着相较于浅层模型显然的优势. 深度学习善于从原始输入数据中 …
它在特征提取和模型拟合上都有着相较于浅层模型显然的优势. 深度学习善于从原始输入数据中 …
Short-term output power forecasting of photovoltaic systems based on the deep belief net
LL Li, P Cheng, HC Lin, H Dong - Advances in mechanical …, 2017 - journals.sagepub.com
Photovoltaic power is now a major green energy resource, and its generated power can be
directly connected to the power grid. However, the stability of power grid may be affected by …
directly connected to the power grid. However, the stability of power grid may be affected by …
基于SVD 和DBN 的水电机组故障诊断
李辉, 范智超, 李华, 白亮, 贾嵘, 罗兴锜 - 水力发电学报, 2020 - slfdxb.cn
针对水电机组早期故障信号信噪比低的问题, 本文将奇异值分解(SVD) 和深度置信网络(DBN)
相结合进行故障诊断. 首先, 利用包含噪声的振动信号构造Hankel 矩阵, 对其进行奇异值分解 …
相结合进行故障诊断. 首先, 利用包含噪声的振动信号构造Hankel 矩阵, 对其进行奇异值分解 …
[PDF][PDF] 用于局部放电模式的深度置信网络方法
张新伯, 唐炬, 潘成, 张晓星, 金淼, 杨东, 郑建… - 电网技术, 2016 - softdown.elecfans.net
气体绝缘电器(gas insulated switchgear, GIS) 内部绝缘缺陷产生的局部放电(partial discharge,
PD), 特征表现较复杂, 分散性大, 易受运行环境影响, 而基于PD 统计特征模式识别的传统方法 …
PD), 特征表现较复杂, 分散性大, 易受运行环境影响, 而基于PD 统计特征模式识别的传统方法 …
Research on point-wise gated deep networks
Abstract Stacking Restricted Boltzmann Machines (RBM) to create deep networks, such as
Deep Belief Networks (DBN) and Deep Boltzmann Machines (DBM), has become one of the …
Deep Belief Networks (DBN) and Deep Boltzmann Machines (DBM), has become one of the …