《NeuralNetworksandDeepLearning》（美）MichaelNielsen著英文版.pdf_DeepNeuralNetworks下载-深度学习文档类

需积分: 5 446 浏览量更新于2023-05-26 评论 1 收藏 13.21MB PDF 举报

身份认证购VIP最低享 7 折!

领优惠券(最高得80元）

资源详情

资源评论

资源推荐

2016/10/10 Neural networks and deep learning

http://neuralnetworksanddeeplearning.com/index.html 1/2

NeuralNetworksandDeepLearning is a free online book. The

book will teach you about:

Neural networks, a beautiful biologically-inspired

programming paradigm which enables a computer to learn

from observational data

Deep learning, a powerful set of techniques for learning in

neural networks

Neural networks and deep learning currently provide the best

solutions to many problems in image recognition, speech

recognition, and natural language processing. This book will teach

you many of the core concepts behind neural networks and deep

learning.

For more details about the approach taken in the book, see here. Or

you can jump directly to Chapter 1 and get started.

Neural Networks and Deep Learning

Neural Networks and Deep earning

hat this book is about

On the eercises and problems

sing neural nets to recognie

handwritten digits

ow the backpropagation

algorithm works

mproving the way neural

networks learn

 visual proof that neural nets can

compute any function

hy are deep neural networks

hard to train

Deep learning

ppendi: s there a siple

algorithm for intelligence

cknowledgements

Frequently sked uestions

f you benefit from the book, please

make a small donation.  suggest ,

but you can choose the amount.

Sponsors

Thanks to all the supporters who

made the book possible, with

especial thanks to avel Dudrenov.

Thanks also to all the contributors to

the ugfinder all of Fame.

Resources

ook F

Code repository

ichael Nielsens project

announcement mailing list

Deep earning, draft book in

preparation, by oshua engio, an

oodfellow, and aron Courville

欧拉的博客:www.liuhao.me

2016/10/10 Neural networks and deep learning

http://neuralnetworksanddeeplearning.com/aout.html 1/

Neural networks are one of the most beautiful programming

paradigms ever invented. n the conventional approach to

programming, we tell the computer what to do, breaking big

problems up into many small, precisely defined tasks that the

computer can easily perform. y contrast, in a neural network we

dont tell the computer how to solve our problem. nstead, it learns

from observational data, figuring out its own solution to the

roblem at hand.

utomatically learning from data sounds promising. owever, until

 we didnt know how to train neural networks to surpass more

traditional approaches, ecept for a few specialied problems. hat

changed in  was the discovery of techniques for learning in so-

called deep neural networks. These techniques are now known as

deep learning. Theyve been developed further,

and today deep

neural networks and deep learning achieve outstanding

performance on many important problems in computer vision,

speech recognition, and natural language processing. Theyre being

deployed on a large scale by companies such as oogle, icrosoft,

and Facebook.

The purpose of this book is to help you master the core concepts of

neural networks, including modern techniques for deep learning.



fter working through the book you will have written code that uses

neural networks and deep learning to solve comple pattern

recognition problems. nd you will have a foundation to use neural

networks and deep learning to attack problems of your own

devising.

 prinipleoriented approa

One conviction underlying the book is that its better to obtain a

solid understanding of the core principles of neural networks and

eep learning, rather than a hay understanding of a long laundry

list of ideas. f youve understood the core ideas well, you can

rapidly understand other new material. n programming language

terms, think of it as mastering the core synta, libraries and data

structures of a new language. ou may still only know a tiny

at tis ook is aout

Neural Networks and Deep earning

hat this book is about

On the eercises and problems

sing neural nets to recognie

handwritten digits

ow the backpropagation

algorithm works

mproving the way neural

networks learn

 visual proof that neural nets can

compute any function

hy are deep neural networks

hard to train

Deep learning

ppendi: s there a siple

algorithm for intelligence

cknowledgements

Frequently sked uestions

f you benefit from the book, please

make a small donation.  suggest ,

but you can choose the amount.

Sponsors

Thanks to all the supporters who

made the book possible, with

especial thanks to avel Dudrenov.

Thanks also to all the contributors to

the ugfinder all of Fame.

Resources

ook F

Code repository

ichael Nielsens project

announcement mailing list

Deep earning, draft book in

preparation, by oshua engio, an

oodfellow, and aron Courville

欧拉的博客:www.liuhao.me

2016/10/10 Neural networks and deep learning

http://neuralnetworksanddeeplearning.com/aout.html 2/

fraction of the total language - many languages have enormous

standard libraries - but new libraries and data structures can be

understood quickly and easily.

This means the book is emphatically not a tutorial in how to use

some particular neural network library. f you mostly want to learn

your way around a library, dont read this book Find the library you

wish to learn, and work through the tutorial

s and documentation.

ut be warned. hile this has an immediate problem-solving

payoff, if you want to understand whats really going on in neural

networks, if you want insights that will still be relevant years from

now, then its not enough just to learn some hot library. ou need to

understand the durable, lasting insights underlying how neural

networks work. Technologies come and technologies go, bu

t insight

is forever.

 andson approa

ell learn the core principles behind neural networks and deep

learning by attacking a concrete problem: the problem of teaching a

computer to recognie handwritten digits. This problem is

etremely difficult to solve using the conventional approach to

programming. nd yet, as well see, it can be solved pretty well

using a simple neural network, with just a few

tens of lines of code,

and no special libraries. hats more, well improve the program

through many iterations, gradually incorporating more and more of

the core ideas about neural networks and deep learning.

This hands-on approach means that youll need some programming

eperience to read the book. ut you dont need to be a professional

programmer. ve written the code in ython version ., which

even if you dont program in ython, should be easy to understand

with just a little effort. Through the course of the book we will

develop a little neural network library, which you can use to

eperiment and to build understanding. ll the code is available for

download here. Once youve finished the book, or as you read it, you

can easily pick up one of the more feature-complete neural network

librar

ies intended for use in production.

On a related note, the mathematical requirements to read the book

are modest. There is some mathematics in most chapters, but its

y ichael Nielsen  an 1

欧拉的博客:www.liuhao.me

2016/10/10 Neural networks and deep learning

http://neuralnetworksanddeeplearning.com/aout.html /

usually just elementary algebra and plots of functions, which 

epect most readers will be okay with.  occasionally use more

advanced mathematics, but have structured the material so you can

follow even if some mathematical details elude you. The one

chapter which uses heavier mathematics etensively is Chapter ,

which requires a little multivariable calculus and linear algebra. f

those arent famil

iar,  begin Chapter  with a discussion of how to

navigate the mathematics. f youre finding it really heavy going,

you can simply skip to the summary of the chapters main results.

n any case, theres no need to worry about this at the outset.

ts rare for a book to aim to be both principle-oriented and hands-

on. ut  believe youll learn best if we build out the fundamental

ideas of neural netwo

rks. ell develop living code, not just abstract

theory, code which you can eplore and etend. This way youll

understand the fundamentals, both in theory and practice, and be

well set to add further to your knowledge.

ncecorpesecesoosceeseneureorsneepernn

eernonress

sorscenseunerreeoonsruononoercnporecensesens

ourereeocopsrenuonsoounooseoureneresencoercusepese

conce

supern

欧拉的博客:www.liuhao.me

剩余291页未读，继续阅读

Notus6

粉丝: 3
资源: 7

会员权益专享

《Neural Networks and Deep Learning》（美）Michael Nielsen 著英文版.pdf

评论0

会员权益专享

最新资源

《Neural Networks and Deep Learning》（美）Michael Nielsen 著 英文版.pdf

评论0

neural networks and deep learning 这本书怎么样？

neural networks and deep learning --michael nielsen

tensorflow for deep learning.pdf

刘知远-Introduction to Graph Neural Networks.pdf

Deep Learning Practical Neural Networks with Java 无水印pdf

下载Mastering Machine Learning with Python in Six Steps 英文高清完整.pdf 版

Introduction.to.Deep.Learning.with.complete.Python.and.TensorFlow.examples

Deep Learning for Beginners

ieee transactions on neural networks and learning systems

【高清带书签目录pdf】Deep Learning with PyTorch

Deep Learning with Keras 2017

Python Deep Learning - Valentino Zocca

MATLAB Deep Learning: With Machine Learning, Neural Networks and AI

Deep Learning for Image Processing Applications

推荐20个姿态估计深度学习模型

大学英语 真题 neural network-deep learning

Python Deep Learning Projects

Practical Machine Learning and Image Processing

会员权益专享

最新资源

《Neural Networks and Deep Learning》（美）Michael Nielsen 著英文版.pdf

大学英语真题 neural network-deep learning