DBN是一种堆叠许多独立的无监督网络的技术,这种网络使用每个网络的隐藏层作为下一层的输入。通常,使用受限玻尔兹曼机(RBM)或自动编码器的“堆栈” 。

VIP内容

论文题目

深度学习对设计模式组织自动化的影响:Implications of deep learning for the automation of design patterns organization

论文简介

虽然像其它领域,如电子邮件过滤,网页分类,情感分析,和作者识别,研究人员已经使用文本分类方法自动化组织和选择设计模式。然而,有必要在设计模式(即文档)与用于组织设计模式的特征之间的语义关系之间架起桥梁。在本研究中,我们提出了一种利用强大的深度学习算法深度信念网络 (DBN),以特征向量的形式去学习文档的语义表示方法。我们在一个基于文本分类的自动化系统中进行了一个案例研究,该系统用于软件设计模式的分类和选择。在案例研究中,我们重点研究了两个主要的研究目标:1)验证了除了所提出的方法之外,通过基于全局滤波器的特征选择方法构建的特征集的效果,2)利用该方法评估分类器分类决策(即模式组织)的改进效果。DBN参数的调整,例如一些隐藏层、节点和迭代,可以帮助开发人员构建更具说明性的特征集。实验结果表明,该方法对于构造更具代表性的特征集,提高分类器在设计模式组织方面的性能具有重要意义。

关键字

设计模式,深度学习,特征集,性能,分类器

论文作者

Shahid Hussain , Jacky Keung , Arif Ali Khan ,香港大学计算机科学系 Awais Ahmad ,大韩民国京山延南大学信息与通信工程系 Salvatore Cuomo,Francesco Piccialli, 意大利那不勒斯大学 Gwanggil Jeon , 韩国仁川国立大学嵌入式系统工程系 Adnan Akhunzada,巴基斯坦伊斯兰堡通信卫星信息技术研究所

论文翻译链接:https://pan.baidu.com/s/1P6mUE4nkt6ZNUSPFBLQBKw 提取码:0vnr

成为VIP会员查看完整内容
0
5

最新内容

In this paper, we propose a novel architecture for a deep learning system, named k-degree layer-wise network, to realize efficient geo-distributed computing between Cloud and Internet of Things (IoT). The geo-distributed computing extends Cloud to the geographical verge of the network in the neighbor of IoT. The basic ideas of the proposal include a k-degree constraint and a layer-wise constraint. The k-degree constraint is defined such that the degree of each vertex on the h-th layer is exactly k(h) to extend the existing deep belief networks and control the communication cost. The layer-wise constraint is defined such that the layer-wise degrees are monotonically decreasing in positive direction to gradually reduce the dimension of data. We prove the k-degree layer-wise network is sparse, while a typical deep neural network is dense. In an evaluation on the M-distributed MNIST database, the proposal is superior to a state-of-the-art model in terms of communication cost and learning time with scalability.

0
0
下载
预览

最新论文

In this paper, we propose a novel architecture for a deep learning system, named k-degree layer-wise network, to realize efficient geo-distributed computing between Cloud and Internet of Things (IoT). The geo-distributed computing extends Cloud to the geographical verge of the network in the neighbor of IoT. The basic ideas of the proposal include a k-degree constraint and a layer-wise constraint. The k-degree constraint is defined such that the degree of each vertex on the h-th layer is exactly k(h) to extend the existing deep belief networks and control the communication cost. The layer-wise constraint is defined such that the layer-wise degrees are monotonically decreasing in positive direction to gradually reduce the dimension of data. We prove the k-degree layer-wise network is sparse, while a typical deep neural network is dense. In an evaluation on the M-distributed MNIST database, the proposal is superior to a state-of-the-art model in terms of communication cost and learning time with scalability.

0
0
下载
预览
参考链接
Top
微信扫码咨询专知VIP会员