没有合适的资源?快使用搜索试试~ 我知道了~
人工智能-深度学习-基于极速学习机的深度学习在图像分类上的研究.pdf
1.该资源内容由用户上传,如若侵权请联系客服进行举报
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
版权申诉
0 下载量 46 浏览量
2022-06-26
17:27:22
上传
评论
收藏 1.38MB PDF 举报
温馨提示
试读
51页
人工智能-深度学习-基于极速学习机的深度学习在图像分类上的研究.pdf
资源推荐
资源详情
资源评论
摘要
I
摘 要
随着信息技术的不断发展,以神经网络为载体的深度学习逐渐成为了现阶段各种先进
技术的代名词。神经网络技术从上世纪出现以后,各种基于神经网络的模型逐渐用来解决
实际场景中的各种问题。特别是在 2012 年的大规模图像分类竞赛中,基于深度学习的模
型将分类结果提升了 11 个百分点以后,便促进了现阶段深度学习浪潮的形成。深度学习技
术将人们从繁杂的人工设计特征转换成了自动学习有效特征,强化模型抽象学习的能力,
极大的促进了图像识别、图像检测、语音识别、追踪等技术的发展。
极速学习机自从 2004 年提出以来,在过去的十几年间,有了长足的发展。首先各种
理论研究的出现为极速学习机的发展奠定了坚实的基础,其次基于极速学习机的应用,将
其拓展到了真实场景中。不过在极速学习机中,不管从权值初始化还是更为有效的特征表
达以及深度学习模型上,都有许多问题需要解决。
本文从极速学习机入手,探索了其权值初始化和分布式表达,并且提出并验证了卷积
极速学习机。本文将通过如下三个方面开展:
首先,对权值初始化进行了研究,探究了权值初始化对于极速学习机的影响。所提出
的方法可以解决极速学习机的随机特征表达不具有紧凑性和判别性的问题,同时为其他方
法提出了一个快速有效的权值初始化的解决方案;
其次,对于极速学习机的特征表达进行了研究。分布式表达是特征表达中比较常用的
方式,在极速学习机不需要权值调整的前提下,提出了基于极速学习机的分布式特征表达
方式,不但可以将类别信息通过特征组合引入模型结构中,而且提高了极速学习机的性能;
最后,通过对于全链接和卷积神经网络关联的探究,提出了基于分布式表达的卷积极
速学习机,将极速学习机从卷积方面拓展到了深度学习层面。卷积学习由于是对于局部感
受野的学习,能够保留更多的局部信息,使其特征表达方式更为具有代表性。极速学习机
便通过卷积化的操作,获得了更为抽象和具有代表性的卷积层特征。这不但将卷积学习和
极速学习机进行了融合,而且所提出的结构也取得了非常好的结果。
关键词:极速学习机,卷积神经网络,分布式表达,权值初始化
万方数据
Abstract
II
Abstract
With the development of the information technology, Deep Learning based on neural
networks has become the synonym of all kinds of advanced technology. Since the neural network
technology appeared in the last century, so many models based on neural networks have been
used to solve different problems in real world. Especially in 2012, the models based on deep
learning raised the accuracy by 11 percent, in the ImageNet Large Scale Visual Recognition
Challenge (ILSVRC), which led to a new wave of deep learning. Deep learning can learn
effective feature automatically instead of obtaining feature artificially, which can reinforce the
ability of abstract learning, where the deep learning improve the development of image detection,
image recognition, speech recognition, tracking and so on.
Extreme learning machine was proposed in 2004, and in past decades, has made great
strides forward. First of all, many theories have proposed to support the development of the
extreme learning machine; Secondly, extreme learning machine has been extended to real world
to solve real problems. But in extreme learning machine, no matter in weights initialization,
feature representation and in deep learning, there are many optimized problems need to be
solved.
This paper has explored the extreme learning machine and tried to solve three problems:
First of all, this paper has explored the weight initialization of extreme learning machine
and tried to illustrate the effect when different methods are used. The proposed method solves
the problem that the random generated feature is lack of compactness and discriminant, and
provides a fast and effective method to initialize a neural network model.
Secondly, this paper has explored the feature representation of extreme learning. Distributed
representation is a common method in feature representation. Without tuning the weights of
extreme learning machine iteratively, this paper has proposed the distributed representation
based on extreme learning machine. It not only adds the category information into the model by
combining the features, but also improves the performance of extreme learning machine.
Thirdly, this paper has explored the relationship between fully connected neural networks
and convolutional neural networks and proposed the convolutional extreme learning machine
based on distributed representation, and extend extreme learning machine to the deep learning
field in the aspect of convolution. Convolutional learning can learn more local information using
the local receptive fields, which can learn a more represented feature. Extreme learning machine
万方数据
Abstract
III
can obtain more abstract and represented convolutional feature by using convolutional operation.
It is not only a fusion of extreme learning machine and convolutional neural networks, but also
achieves an excellent performance.
Key Words: Extreme Learning Machine, Convolutional Neural Networks, Distributed
Representation, Weights Initialization
万方数据
目录
1
目录
摘 要 ................................................................................................................................................ I
Abstract .......................................................................................................................................... II
第 1 章 引言 ................................................................................................................................. 1
1.1. 研究背景和意义 ........................................................................................................... 1
1.1.1. 人工神经网络 ..................................................................................................... 1
1.1.2. 极速学习机 ......................................................................................................... 3
1.1.3. 研究意义 ............................................................................................................. 5
1.2. 国内外发展现状与趋势 ............................................................................................... 5
1.2.1. 极速学习机发展现状与趋势 ............................................................................ 5
1.2.2. 深度学习发展现状与趋势 ................................................................................ 7
1.2.3. 本文所使用数据库介绍 .................................................................................. 10
1.3. 本文主要贡献 ............................................................................................................. 12
1.4. 本文组织结构 ............................................................................................................. 12
第 2 章 权值微调的极速学习自动编码机 ............................................................................... 13
2.1. 回顾极速学习机 ......................................................................................................... 13
2.1.1. 自动编码机 ....................................................................................................... 13
2.1.2. 极速学习机 ....................................................................................................... 14
2.1.3. 极速学习自动编码机机 ................................................................................... 15
2.2. 本章所提出的方法介绍 ............................................................................................. 15
2.3. 性能评估 ..................................................................................................................... 17
2.3.1. 各方法性能评估 ............................................................................................... 18
2.3.2. 时空开销评估 ................................................................................................... 18
2.3.3. 深度模型性能评估 ........................................................................................... 19
2.4. 本章小结 ..................................................................................................................... 21
第 3 章 类别约束极速学习机 ................................................................................................... 22
3.1. 分布式表达 ................................................................................................................. 22
3.2. 本章所提出的方法介绍 ............................................................................................. 23
3.3. 性能评估 ..................................................................................................................... 26
3.3.1. 在 MNIST 数据集上的性能评估 .................................................................... 27
3.3.2. 在 CIFAR-10 数据集上的性能评估 ................................................................ 28
3.4. 本章小结 ..................................................................................................................... 30
万方数据
目录
2
第 4 章 卷积极速学习机 ........................................................................................................... 31
4.1. 卷积神经网络 ............................................................................................................. 31
4.1.1. 卷积操作 ........................................................................................................... 31
4.1.2. Pooling 操作 ...................................................................................................... 32
4.2. 本章所提出的方法介绍 ............................................................................................. 34
4.2.1. 卷积神经网络与全连接神经网络 ................................................................... 34
4.2.2. 卷积极速学习机 ............................................................................................... 35
4.3. 性能评估 ..................................................................................................................... 36
4.4. 本章小结 ..................................................................................................................... 38
第 5 章 总结与展望 ................................................................................................................... 40
5.1. 本文工作总结 ............................................................................................................. 40
5.2. 下一步研究方向 ......................................................................................................... 40
参考文献 ....................................................................................................................................... 42
在读期间发表的学术论文及研究成果 ....................................................................................... 48
致谢 ............................................................................................................................................... 49
万方数据
剩余50页未读,继续阅读
资源评论
programhh
- 粉丝: 8
- 资源: 3838
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功