# Deep Learning - The Straight Dope (*Deprecated* Please see d2l.ai)
## This content has been moved to Dive into the Deep Learning Book freely available at https://d2l.ai/.
## Abstract
This repo contains an
incremental sequence of notebooks designed to teach deep learning, MXNet, and
the ``gluon`` interface. Our goal is to leverage the strengths of Jupyter
notebooks to present prose, graphics, equations, and code together in one place.
If we're successful, the result will be a resource that could be simultaneously
a book, course material, a prop for live tutorials, and a resource for
plagiarising (with our blessing) useful code. To our knowledge there's no source
out there that teaches either (1) the full breadth of concepts in modern deep
learning or (2) interleaves an engaging textbook with runnable code. We'll find
out by the end of this venture whether or not that void exists for a good
reason.
Another unique aspect of this book is its authorship process. We are
developing this resource fully in the public view and are making it available
for free in its entirety. While the book has a few primary authors to set the
tone and shape the content, we welcome contributions from the community and hope
to coauthor chapters and entire sections with experts and community members.
Already we've received contributions spanning typo corrections through full
working examples.
## Implementation with Apache MXNet
Throughout this book,
we rely upon MXNet to teach core concepts, advanced topics, and a full
complement of applications. MXNet is widely used in production environments
owing to its strong reputation for speed. Now with ``gluon``, MXNet's new
imperative interface (alpha), doing research in MXNet is easy.
## Dependencies
To run these notebooks, you'll want to build MXNet from source. Fortunately,
this is easy (especially on Linux) if you follow [these
instructions](http://mxnet.io/get_started/install.html). You'll also want to
[install Jupyter](http://jupyter.readthedocs.io/en/latest/install.html) and use
Python 3 (because it's 2017).
## Slides
The authors (& others) are
increasingly giving talks that are based on the content in this books. Some of
these slide-decks (like the 6-hour KDD 2017) are gigantic so we're collecting
them separately in [this repo](https://github.com/zackchase/mxnet-slides).
Contribute there if you'd like to share tutorials or course material based on
this books.
## Translation
As we write the book, large stable sections are simultaneously being translated into 中文,
available in a [web version](http://zh.gluon.ai/) and via [GitHub source](http://zh.gluon.ai/).
## Table of contents
### Part 1: Deep Learning Fundamentals
* **Chapter 1:** Crash course
* [Preface](https://github.com/zackchase/mxnet-the-straight-dope/blob/master/chapter01_crashcourse/preface.ipynb)
* [Introduction](https://github.com/zackchase/mxnet-the-straight-dope/blob/master/chapter01_crashcourse/introduction.ipynb)
* [Manipulating data with NDArray](https://github.com/zackchase/mxnet-the-straight-dope/blob/master/chapter01_crashcourse/ndarray.ipynb)
* [Linear algebra](https://github.com/zackchase/mxnet-the-straight-dope/blob/master/chapter01_crashcourse/linear-algebra.ipynb)
* [Probability and statistics](https://github.com/zackchase/mxnet-the-straight-dope/blob/master/chapter01_crashcourse/probability.ipynb)
* [Automatic differentiation via ``autograd``](https://github.com/zackchase/mxnet-the-straight-dope/blob/master/chapter01_crashcourse/autograd.ipynb)
* **Chapter 2:** Introduction to supervised learning
* [Linear regression *(from scratch)*](https://github.com/zackchase/mxnet-the-straight-dope/blob/master/chapter02_supervised-learning/linear-regression-scratch.ipynb)
* [Linear regression *(with ``gluon``)*](https://github.com/zackchase/mxnet-the-straight-dope/blob/master/chapter02_supervised-learning/linear-regression-gluon.ipynb)
* [Binary classification with logistic regression *(``gluon`` w bespoke loss function)*](https://github.com/zackchase/mxnet-the-straight-dope/blob/master/chapter02_supervised-learning/logistic-regression-gluon.ipynb)
* [Multiclass logistic regression *(from scratch)*](https://github.com/zackchase/mxnet-the-straight-dope/blob/master/chapter02_supervised-learning/softmax-regression-scratch.ipynb)
* [Multiclass logistic regression *(with ``gluon``)*](https://github.com/zackchase/mxnet-the-straight-dope/blob/master/chapter02_supervised-learning/softmax-regression-gluon.ipynb)
* [Overfitting and regularization *(from scratch)*](https://github.com/zackchase/mxnet-the-straight-dope/blob/master/chapter02_supervised-learning/regularization-scratch.ipynb)
* [Overfitting and regularization *(with ``gluon``)*](https://github.com/zackchase/mxnet-the-straight-dope/blob/master/chapter02_supervised-learning/regularization-gluon.ipynb)
* [Perceptron and SGD primer](https://github.com/zackchase/mxnet-the-straight-dope/blob/master/chapter02_supervised-learning/perceptron.ipynb)
* [Learning environments](https://github.com/zackchase/mxnet-the-straight-dope/blob/master/chapter02_supervised-learning/environment.ipynb)
* **Chapter 3:** Deep neural networks (DNNs)
* [Multilayer perceptrons *(from scratch)*](https://github.com/zackchase/mxnet-the-straight-dope/blob/master/chapter03_deep-neural-networks/mlp-scratch.ipynb)
* [Multilayer perceptrons *(with ``gluon``)*](https://github.com/zackchase/mxnet-the-straight-dope/blob/master/chapter03_deep-neural-networks/mlp-gluon.ipynb)
* [Dropout regularization *(from scratch)*](https://github.com/zackchase/mxnet-the-straight-dope/blob/master/chapter03_deep-neural-networks/mlp-dropout-scratch.ipynb)
* [Dropout regularization *(with ``gluon``)*](https://github.com/zackchase/mxnet-the-straight-dope/blob/master/chapter03_deep-neural-networks/mlp-dropout-gluon.ipynb)
* [Introduction to ``gluon.Block`` and ``gluon.nn.Sequential()``](https://github.com/zackchase/mxnet-the-straight-dope/blob/master/chapter03_deep-neural-networks/plumbing.ipynb)
* [Writing custom layers with ``gluon.Block``](https://github.com/zackchase/mxnet-the-straight-dope/blob/master/chapter03_deep-neural-networks/custom-layer.ipynb)
* [Serialization: saving and loading models](https://github.com/zackchase/mxnet-the-straight-dope/blob/master/chapter03_deep-neural-networks/serialization.ipynb)
* Advanced Data IO
* Debugging your neural networks
* **Chapter 4:** Convolutional neural networks (CNNs)
* [Convolutional neural networks *(from scratch)*](https://github.com/zackchase/mxnet-the-straight-dope/blob/master/chapter04_convolutional-neural-networks/cnn-scratch.ipynb)
* [Convolutional neural networks *(with ``gluon``)*](https://github.com/zackchase/mxnet-the-straight-dope/blob/master/chapter04_convolutional-neural-networks/cnn-gluon.ipynb)
* [Introduction to deep CNNs (AlexNet)](https://github.com/zackchase/mxnet-the-straight-dope/blob/master/chapter04_convolutional-neural-networks/deep-cnns-alexnet.ipynb)
* [Very deep networks and repeating blocks (VGG network)](https://github.com/zackchase/mxnet-the-straight-dope/blob/master/chapter04_convolutional-neural-networks/very-deep-nets-vgg.ipynb)
* [Batch normalization *(from scratch)*](https://github.com/zackchase/mxnet-the-straight-dope/blob/master/chapter04_convolutional-neural-networks/cnn-batch-norm-scratch.ipynb)
* [Batch normalization *(with ``gluon``)*](https://github.com/zackchase/mxnet-the-straight-dope/blob/master/chapter04_convolutional-neural-networks/cnn-batch-norm-gluon.ipynb)
* **Chapter 5:** Recurrent neural networks (RNNs)
* [Simple RNNs (from scratch)](https://github.com/zackchase/mxnet-the-straight-dope/blob/master/chapter05_recurrent-neural-networks/simple-rnn.ipynb)
* [LSTMS RNNs (from scratch)](https://github.com/zackchase/mxnet-the-straight-dope/blob/master/chapter05_recurrent-neural-networks/lstm-scratch.ipynb)
* [GRUs (from
没有合适的资源?快使用搜索试试~ 我知道了~
温馨提示
这是(深度学习框架MXnet)mxnet-the-straight-dope-master的一些资料。关于如何安装mxnet模块,这个我在博客中记录过,欢迎大家交流学习。
资源推荐
资源详情
资源评论
收起资源包目录
(深度学习框架MXnet)mxnet-the-straight-dope-master.zip (203个子文件)
gluon.css 152B
house_pred_train.csv 450KB
house_pred_test.csv 441KB
.gitattributes 134B
.gitignore 1KB
.gitignore 20B
regularization.graffle 2KB
object-detection.ipynb 838KB
pixel2pixel.ipynb 760KB
vae-gluon.ipynb 528KB
proto-P02-C02.6-loss.ipynb 304KB
intro-forecasting-gluon.ipynb 288KB
visual-question-answer.ipynb 230KB
gan-intro.ipynb 216KB
probability.ipynb 203KB
kaggle-gluon-kfold.ipynb 192KB
kaggle-gluon-kfold.ipynb 191KB
perceptron.ipynb 175KB
gd-sgd-scratch.ipynb 145KB
gd-sgd-gluon.ipynb 134KB
issm-scratch.ipynb 109KB
lds-scratch.ipynb 87KB
linear-regression-scratch.ipynb 80KB
bayes-by-backprop.ipynb 64KB
DQN.ipynb 64KB
introduction.ipynb 57KB
momentum-scratch.ipynb 51KB
optimization-intro.ipynb 48KB
rmsprop-scratch.ipynb 45KB
rmsprop-gluon.ipynb 44KB
momentum-gluon.ipynb 40KB
linear-regression-gluon.ipynb 40KB
bayes-by-backprop-rnn.ipynb 39KB
linear-algebra.ipynb 39KB
simple-rnn.ipynb 37KB
conditional.ipynb 36KB
adagrad-scratch.ipynb 31KB
adam-scratch.ipynb 31KB
adadelta-scratch.ipynb 30KB
adagrad-gluon.ipynb 30KB
adam-gluon.ipynb 29KB
adadelta-gluon.ipynb 29KB
tree-lstm.ipynb 28KB
bayes-by-backprop-gluon.ipynb 27KB
chapter-one-problem-set.ipynb 27KB
chapter-one-problem-set-checkpoint.ipynb 27KB
fine-tuning.ipynb 26KB
hybridize.ipynb 26KB
Graph-Neural-Networks.ipynb 25KB
intro-forecasting-2-gluon.ipynb 25KB
ndarray.ipynb 24KB
DDQN.ipynb 24KB
cnn-batch-norm-scratch.ipynb 24KB
softmax-regression-scratch.ipynb 24KB
multiple-gpus-scratch.ipynb 23KB
regularization-scratch.ipynb 23KB
deep-cnns-alexnet.ipynb 21KB
custom-layer.ipynb 19KB
softmax-regression-gluon.ipynb 19KB
mlp-scratch.ipynb 19KB
logistic-regression-gluon.ipynb 19KB
environment.ipynb 18KB
tensor_basics.ipynb 18KB
rnns-gluon.ipynb 18KB
mlp-dropout-scratch.ipynb 17KB
cnn-scratch.ipynb 15KB
lstm-scratch.ipynb 15KB
dcgan.ipynb 15KB
gru-scratch.ipynb 15KB
plumbing.ipynb 13KB
mlp-gluon.ipynb 13KB
mlp-dropout-gluon.ipynb 12KB
regularization-gluon.ipynb 11KB
multiple-gpus-gluon.ipynb 11KB
training-with-multiple-machines.ipynb 9KB
very-deep-nets-vgg.ipynb 9KB
autograd-checkpoint.ipynb 8KB
autograd.ipynb 8KB
serialization.ipynb 8KB
cnn-batch-norm-gluon.ipynb 8KB
intro-recommender-systems.ipynb 7KB
preface.ipynb 7KB
cnn-gluon.ipynb 7KB
introduction-to-recommender-systems.ipynb 4KB
gtx-580-gpu.jpeg 25KB
imagenet.jpeg 20KB
legendre.jpeg 7KB
real_hotdog.jpg 1.03MB
tensor_cartoon.jpg 204KB
cat2.jpg 176KB
catdog.jpg 98KB
pikachu.jpg 88KB
taxonomy.jpg 82KB
road-cliff.jpg 75KB
dog2.jpg 60KB
cat1.jpg 52KB
berliner.jpg 42KB
leg_hotdog.jpg 39KB
dog-cartoon2.jpg 34KB
whitecat320.jpg 34KB
共 203 条
- 1
- 2
- 3
资源评论
追光者♂
- 粉丝: 2w+
- 资源: 516
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
最新资源
- Flume进阶-自定义拦截器jar包
- Dubins曲线算法讲解和在运动规划中的使用.pdf
- 上市公司-股票性质数据-工具变量(民企、国企、央企)2003-2022年.dta
- 上市公司-股票性质数据-工具变量(民企、国企、央企)2003-2022年.xlsx
- Reeds+Shepp曲线算法讲解和实现.pdf
- 毕业设计基于SpringBoot+MyBatisPlus+MySQL+Vue的外卖配送信息系统源代码+数据库
- 词向量(Word Embeddings)是自然语言处理(NLP)领域的一种重要技术.txt
- Surfer,线性函数
- MyBatis 的动态 SQL 是其核心特性之一.txt
- 时代的sdddsddsddsd
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
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