您所在位置网站首页 > 海量文档  > 理工科 > 数理学

迁移学习经典论文Chapter 28 - Neural Networks Part I Unsupervised Learning.pdf 11页

本文档一共被下载: ,您可全文免费在线阅读后下载本文档。

  • 支付并下载
  • 收藏该文档
  • 百度一下本文档
  • 修改文档简介


C H A P T E R 28 Neural Networks Part I: Unsupervised Learning 28.1. GOALS OF THIS CHAPTER This chapter has two goals that are of equal importance. The first goal is to become famil- iar with the general concept of unsupervised neural networks and how they may relate to certain forms of synaptic plasticity in the nervous system. The second goal is to learn how to apply neural networks using Neural Networks Toolbox built into the MATLABW software to address a particular problem. 28.2. BACKGROUND Neural networks have assumed a central role in a variety of fields. The nature of this role is fundamentally dualistic. On the one hand, neural networks can provide powerful models of elementary processes in the brain, including processes of plasticity and learning. On the other hand, they provide solutions to a broad range of specific problems in applied engi- neering, such as speech recognition, financial forecasting, or object classification. 28.2.1. But What Is a Neural Network? Despite the “biological” sounding name, neural networks are actually quite abstract com- puting structures. In fact, they are sometimes referred to as artificial neural networks. Essen- tially, they consist of rather simple computational elements that are connected to each other in various ways to serve a certain function. The architecture of these networks was inspired by mid- to late-20th century notion of brain function, hence, the term neural. At its conceptual core, a unit in a neural network consists of three things (see Figure 28.1): 307 308 28. NEURAL NETWORKS PART I: UNSUPERVISED LEARNING i1 b i2


用户名: 验证码: 点击我更换图片

“原创力文档”前称为“文档投稿赚钱网”,本站为“文档C2C交易模式”,即用户上传的文档直接卖给(下载)用户,本站只是中间服务平台,本站所有文档下载所得的收益归上传人(含作者)所有【成交的100%(原创)】。原创力文档是网络服务平台方,若您的权利被侵害,侵权客服QQ:3005833200 电话:19940600175 欢迎举报,上传者QQ群:784321556