Deep Learning从入门到出世（二）

最新推荐文章于 2023-12-04 19:58:59 发布
最新推荐文章于 2023-12-04 19:58:59 发布
阅读量276 收藏
点赞数
分类专栏： DeepLearning 文章标签： 网络 深度学习 神经网络 机器学习
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/longwoo1012/article/details/106736840
版权

Deep Learning 圣经

二. 深度网络：现代实践

这一部分是炼丹师需要掌握的核心知识，介绍了深度前馈网络，卷积网络， 循环和递归网络，实践性很强的调参技巧如深度学习的正则化，深度模型中的优化方法等等。对于长时间耕耘炼丹这一领域，是需要反复研读实践的。每个点都是可以深入坑。

1. 深度学习的模型

  • 前馈网络
  • 卷积网络
  • 循环网络
  • 递归网络
  • 生成对抗网络

2. 深度学习的正则化

  • L 1 L^1 L1和 L 2 L^2 L2范数的正则化
  • 数据集增强
  • 注入噪声
  • 提前终止
  • 参数绑定和参数共享
  • 稀疏表示
  • Dropout

3. 深度学习的优化

  • SGD
  • 带动量的SGD
  • Adam
  • 牛顿法
  • 共轭梯度
  • BFGS
- [1] Pattern Recognition and Mechine Learning. Christopher M.Bishop. Spring 2006.
- [2] Deep Learning. Ian Goodfellow. MIT Press 2016
- [3] Numerical Optimization.Jorge Nocedal and Stephen J.Wright.Springer 1999.
- [4] Convex Optimization. Stephen Boyd. Cambridge University Press 2004.
- [5] Machine Learning in Action. Peter Harrington. 2013.
卡列宁在睡觉
关注
  • 0
    点赞
  • 踩
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
专栏目录
Deep Learning, Vol. 1: From Basics to Practice
01-06
Deep Learning, Vol. 1: From Basics to Practice By 作者: Andrew Glassner Pub Date: 2018 ISBN: n/a Pages: (909 of 1750) Language: English Format: PDF People are using the tools of deep learning to change how we think about science, art, engineering, business, medicine, and even music. This book is for people who want to understand this field well enough to create deep learning systems, train them, and then use them with confidence to make their own contributions. The book takes a friendly, informal approach. Our goal is to make the ideas of this field simple and accessible to everyone, as shown in the Contents below. Since most practitioners today use one of several free, open-source deep-learning libraries to build their systems, the hard part isn’t in the programming. Rather, it’s knowing what tools to use, and when, and how. Building a working deep learning system requires making a series of technically informed choices, and with today’s tools, those choices require understanding what’s going on under the hood. This book is designed to give you that understanding. You’ll be able to choose the right kind of architecture, how to build a system that can learn, how to train it, and then how to use it to accomplish your goals. You’ll be able to read and understand the documentation for whatever library you’d like to use. And you’ll be able to follow exciting, on-going breakthroughs as they appear, because you’ll have the knowledge and vocabulary that let you read new material, and discuss it with other people doing deep learning. The book is extensively illustrated with over 1000 original figures. They are also all available for free download, for your own use. You don’t need any previous experience with machine learning or deep learning for this book. You don’t need to be a mathematician, because there’s nothing in the book harder than the occasional multiplication. You don’t need to choose a particular programming language, or library, or piece of hardware, because our approach is largely independent of those things. Our focus is on the principles and techniques that are applicable to any language, library, and hardware. Even so, practical programming is important. To stay focused, we gather our programming discussions into 3 chapters that show how to use two important and free Python libraries. Both chapters come with extensive Jupyter notebooks that contain all the code. Other chapters also offer notebooks for for every Python-generated figure. Our goal is to give you all the basics you need to understand deep learning, and then show how to use those ideas to construct your own systems. Everything is covered from the ground up, culminating in working systems illustrated with running code. The book is organized into two volumes. Volume 1 covers the basic ideas that support the field, and which form the core understanding for using these methods well. Volume 2 puts these principles into practice. Deep learning is fast becoming part of the intellectual toolkit used by scientists, artists, executives, doctors, musicians, and anyone else who wants to discover the information hiding in their data, paintings, business reports, test results, musical scores, and more.
Deep Learning从入门到出世（一）
longwoo1012的博客
06-13 302
邓布利多的冥想盆有时候还是要拿出来用用从OpenCV到Deep LearningDeep Learning 圣经一.应用数学与机器学习基础1.监督学习如LogisticMarkDown工具保留 从OpenCV到Deep Learning 如前所言看到了Deep Learning微微扬起的嘴角以后，就像突然发现了一片海洋。 Caffe & MxNet & Tensorflow & PyTorch RCNN & FastRCNN & FasterRCNN & M
Deep Learning v0.1 documentation
Tan
05-27 832
LICENSE Deep Learning Tutorials Getting Started Datasets Notation A Primer on Supervised Optimization for Deep Learning Theano/Python Tips Classifying MNIST digits using Logistic Regression
Deep Learning(1)
weixin_39012047的博客
08-25 200
1.概述 Artificial Intelligence，也就是人工智能，就像长生不老和星际漫游一样，是人类最美好的梦想之一。虽然计算机技术已经取得了长足的进步，但是到目前为止，还没有一台电脑能产生“自我”的意识。是的，在人类和大量现成数据的帮助下，电脑可以表现的十分强大，但是离开了这两者，它甚至都不能分辨一个喵星人和一个汪星人。　　 深度学习隶属于机器学习，机器学习已经发展很久，在早些时候没...
[DEEP LEARNING An MIT Press book in preparation]Deep Learning for AI
孙佰贵的专栏
10-08 7616
接触DL已经有半年了，积累了一些实验的经验，也对DL有了一些自己的见解和认识，于是乎想扩宽以及加深DL方面相关的一些知识。然后看到一本MIT出版社正要出版的一本关于DL的书http://www.iro.umontreal.ca/~bengioy/dlbook/，所以就有了读一下这本书然后做点笔记攒点知识量的念头，这一系列的博客将是笔记型的，有什么写的不好之处还望广大博友见谅，也欢迎各位同行能指点一
Deep Learning 入门书籍
02-02
Deep Learning书的教程，是入门深度学习的好资料。。。。。。。。。。。。。。。。。
deep learning
08-25
'Written by three experts in the field, Deep Learning is the only comprehensive book on the subject.' -- Elon Musk, co-chair of OpenAI; co-founder and CEO of Tesla and SpaceX, Deep learning is a form ...
deep learning caffe入门
03-27
关于深度学习书籍 21 天学caffe 的书籍，之前的CSDN的可以下载的文档 非常不清楚 很模糊。还有深度学习的基础书籍以及caffe官网的中译本
Better Deep Learning by Jason Brownlee
06-26
Better Deep Learning Train Faster, Reduce Overfitting, and Make Better Predictions by Jason Brownlee 26 step-by-step lessons, 575 pages. quotes from papers and books. step-by-step tutorial projects. ...
Introduction to Deep Learning.pdf
03-31
Introduction to Deep Learning From Logical Calculus to Artificial Intelligence
Deep.Learning.Vol.1.From.Basics.to.Practice.2018
05-15
Table of Contents Chapter 1 Introduction To Machine Learning Chapter 2 Statistics Chapter 3 Probability Chapter 4 Bayes' Rule Chapter 5 Curves And Surfaces Chapter 6 Information Theory Chapter 7 Classification Chapter 8 Training And Testing Chapter 9 Overfitting And Underfitting Chapter 10 Neurons Chapter 11 Learning And Reasoning Chapter 12 Data Preparation Chapter 13 Classifiers Chapter 14 Ensembles Chapter 15 Scikit-Learn Chapter 16 Feed Forward Networks Chapter 17 Activation Functions Chapter 18 Backpropagation Chapter 19 Optimizers
Deep Learning, Vol. 1 From Basics to Practice 无水印原版pdf
05-23
Deep Learning, Vol. 1 From Basics to Practice 英文无水印原版pdf pdf所有页面使用FoxitReader、PDF-XChangeViewer、SumatraPDF和Firefox测试都可以打开 本资源转载自网络，如有侵权，请联系上传者或csdn删除 查看此书详细信息请在美国亚马逊官网搜索此书
Deep Learning - From basics to practice - Vol. 1
11-07
This is one of my most favorite books that teache deep learning from the very basic to advance level. The book does not emphasize on mathematics but explains the logic behind each deep learning algorithm in plain English. Even if you are the new guy in deep learning or you are already at an advance level, this book is for you. Vol 2 will be coming shortly
Deep Learning Vol 1 From Basics to Practice_带书签.pdf
09-05
Deep Learning Vol 1 From Basics to Practice_带书签.pdf
Bengio写的MIT Press《Deep learning》PDF整理版
07-11
深度学习，MIT，deep learning, Yoshua Bengio,Ian Goodfellow,Aaron Courville
用通俗易懂例子“干掉”RNN与LSTM
nobles007820的博客
05-04 571
用简单例子阐述更易理解枯燥无味的定义，本文由浅入深解析两者的工作机理，为设计程序奠定基础，主要分两部分内容： (i)举例理解循环神经网络(RNN [1], Recurrent Neural Networks) (ii)举例理解长短期记忆网络（LSTM [2] ，Long Short-Term Memory）
Bishop新著 - 深度学习:基础与概念 - 第一章 - 深度学习革命
最新发布
GarryWang1248的博客
12-04 1498
当我们使用平方和误差函数 (1.2) 来拟合多项式时，我们看到了此类误差函数的示例。通过这些更改，我们现在有了一个误差函数，其相对网络中每个参数的导数都可以计算。我们现在可以考虑具有不止一层参数的网络。图 1.15 显示了一个具有两个处理层的简单网络。中间层的节点称为隐藏单元(hidden units)，因为它们的值不会出现在训练集中，训练集中仅提供输入和输出的值。图 1.15 中的每个隐藏单元和每个输出单元都计算由 (1.5) 和 (1.6) 给出的形式的函数。
Bishop新著 - 深度学习:基础与概念 - 前言
GarryWang1248的博客
12-04 1817
大神Bishop最新深度学习巨著
Deep learning：一(基础知识_1)
weixin_34336526的博客
03-14 181
  　　前言: 　　最近打算稍微系统的学习下deep learing的一些理论知识，打算采用Andrew Ng的网页教程UFLDL Tutorial，据说这个教程写得浅显易懂，也不太长。不过在这这之前还是复习下machine learning的基础知识，见网页：http://openclassroom.stanford.edu/MainFolder/CoursePage.php?course=...

“相关推荐”对你有帮助么？

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值