## 后记
> 探索是促进创新的引擎。创新促进经济增长。让我们一起去探索吧。
>
> Edith Widder
在这里,我提供了一个介绍性指南,解释了如何使用 TensorFlow,为这种技术提供热身,这无疑将在迫在眉睫的技术场景中发挥主导作用。 事实上,还有 TensorFlow 的其他替代方案,每个方案最适合特定问题;我想邀请读者探索 TensorFlow 包之外的内容。
这些包有很多不同之处。 有些更专业,有些更不专业。 有些比其他更难安装。 其中一些有很好的文档,而另一些尽管运作良好,但更难找到如何使用它们的详细信息。
重要的是:之后的日子里,TensorFlow 由谷歌发布,我在推文 [49] 中读到了 2010-2014 期间,新的深度学习包每 47 天发布一次,2015 年每 22 天发布一次。 这很惊人,不是吗? 正如我在本书的第一章中提出的那样,作为读者的起点,可以在 Awesome Deep Learning [50] 找到一个广泛的列表。
毫无疑问,2015 年 11 月,随着 Google TensorFlow 的发布,深度学习的格局受到影响,现在它是 Github 上最受欢迎的开源机器学习库 [51]。
请记住,Github 的第二个最着名的机器学习项目是 Scikit-learn [52],事实上的 Python 官方的通用机器学习框架。 这些用户可以通过 Scikit Flow(skflow)[53] 使用 TensorFlow,这是来自 Google 的 TensorFlow 的简化接口。
实际上,Scikit Flow 是 TensorFlow 库的高级包装,它允许使用熟悉的 Scikit-Learn 方法训练和拟合神经网络。 该库涵盖了从线性模型到深度学习应用的各种需求。
在我看来,在 TensorFlow 分布式,TensorFlow 服务和 Scikit Flow 发布后,TensorFlow 将成为事实上的主流深度学习库。
深度学习大大提高了语音识别,视觉对象识别,对象检测和许多其他领域的最新技术水平。 它的未来会是什么? 根据 Yann LeCun,Yoshua Bengio 和 Geoffrey Hilton 在 Nature 杂志上的精彩评论,答案是无监督学习 [54]。 他们期望从长远来看,无监督学习比监督学习更重要。 正如他们所提到的,人类和动物的学习基本上没有受到监督:我们通过观察世界来发现它的结构,而不是通过被告知每个物体的名称。
他们对系统的未来进展有很多期望,系统将 CNN 与递归神经网络(RNN)相结合,并使用强化学习。 RNN 处理一个输入,该输入一次编码一个元素,在其隐藏单元中维护序列的所有过去元素的历史的信息。 对于 TensorFlow 中 RNN 实现的介绍,读者可以查看 TensorFlow 教程中的循环神经网络 [55] 部分。
此外,深度学习还面临许多挑战;训练它们的时间推动了新型超级计算机系统的需求。 为了将最佳的知识分析与新的大数据技术和新兴计算系统的强大功能相结合,以前所未有的速度解释大量异构数据,仍然需要进行大量研究。
科学进步通常是大型社区的跨学科,长期和持续努力的结果,而不是突破,深度学习和机器学习一般也不例外。 我们正在进入一个非常激动人心的跨学科研究时期,其中像巴塞罗那那样的生态系统,如 UPC 和 BSC-CNS,在高性能计算和大数据技术方面具有丰富的知识,将在这个新场景中发挥重要作用。
## 参考
[[1]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref1) The MNIST database of handwritten digits. [Online]. Available at:[http://yann.lecun.com/exdb/mnist](http://yann.lecun.com/exdb/mnist) [Accessed: 16/12/2015].
[[2]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref2)_ Github_, (2016) Fist Contact with TensorFlow. Source code [Online]. Available at:[https://github.com/jorditorresBCN/TutorialTensorFlow](https://github.com/jorditorresBCN/TutorialTensorFlow)[Accessed: 16/12/2015].
[[3]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref3)_ TensorFlow Serving_[Online]. Available at: [http://tensorflow.github.io/serving/](http://tensorflow.github.io/serving/)[Accessed: 24/02/2016].
[[4]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref4) Google Research Blog [Online]. Available at: [http://googleresearch.blogspot.com.es/2016/02/running-your-models-in-production-with.html?m=1](http://googleresearch.blogspot.com.es/2016/02/running-your-models-in-production-with.html?m=1)[Accessed: 24/02/2016].
[[5]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref5)_ TensorFlow Serving_-Architecture Overview[Online]. Available at: [http://tensorflow.github.io/serving/](http://tensorflow.github.io/serving/)[Accessed: 24/02/2016].
[[6]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref6) _TensorFlow Serving_– Serving a TensorFlow Model [Online]. Available at:[http://tensorflow.github.io/serving/serving_basic](http://tensorflow.github.io/serving/serving_basic) [Accessed: 24/02/2016].
[[7]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref7) TensorFlow, (2016) Download & Setup [Online]. Available at: [https://www.tensorflow.org/versions/master/get_started/os_setup.html#download-and-setup](https://www.tensorflow.org/versions/master/get_started/os_setup.html#download-and-setup)[Accessed: 16/12/2015].
[[8]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref8) Wikipedia, (2016). IPython. [Online]. Available at: [https://en.wikipedia.org/wiki/IPython](https://en.wikipedia.org/wiki/IPython) [Accessed: 19/03/2016].
[[9]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref9) TensorFlow: Large-scale machine learning on heterogeneous systems, (2015). [Online]. Available at:[http://download.tensorflow.org/paper/whitepaper2015.pdf](http://download.tensorflow.org/paper/whitepaper2015.pdf)[Accessed: 20/12/2015].
[[10]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref10) TensorFlow, (2016)_Python API – Summary Operations_. [Online]. Available at:[https://www.tensorflow.org/versions/master/api_docs/python/train.html#summary-operations](https://www.tensorflow.org/versions/master/api_docs/python/train.html#summary-operations) [Accessed: 03/01/2016].
[[11]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref11) I recommend using Google Chrome to ensure proper display.
[[12]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref12)TensorFlow, (2016) TensorBoard: Graph Visualization.[Online]. Available at:[https://www.tensorflow.org/versions/master/how_tos/graph_viz/index.html](https://www.tensorflow.org/versions/master/how_tos/graph_viz/index.html)[Accessed: 02/01/2016].
[[13]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref13) One reviewer of this book has indicated that he also had to install the package_python-gi-cairo_.
[[14]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref14) Wikipedia, (2016). Mean Square Error. [Online]. Available at: [https://en.wikipedia.org/wiki/Mean_squared_error](https://en.wikipedia.org/wiki/Mean_squared_error) [Accessed: 9/01/2016].
[[15]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref15) Wikipedia, (2016). Gradient descent. [Online]. Available at: [https://en.wikipedia.org/wiki/Gradient_descent](https://en.wikipedia.org/wiki/Gradient_descent) [Accessed: 9/01/2016].
[[16]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref16) Wikipedia, (2016). Gradient. [Online]. Available at: [https://en.wikipedia.org/wiki/Gradient](https://en.wikipedia.org/wiki/Gradient)[Accessed: 9/01/2016].
[[17]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref17) _Github_, (2016) Book source code [Online]. Available at:[https://github.com/jorditorresBCN/TutorialTensorFlow](https://github.com/jorditorresBCN/TutorialTensorFlow). [Accessed: 16/12/2015].
[[18]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref18) TensorFlow, (2016) API de Python – Tensor Transformations [Online]. Available at:[https://www.tensorflow.org/versions/master/api_docs/python/array_ops.html](https://www.tensorflow.org/versions/master/api_docs/python/array_ops.html) [Accessed: 16/12/2015].
[[19]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref19) TensorFlow, (2016) Tutorial – Reading Data [Online]. Available at:[https://www.tensorflow.org/versions/master/how_tos/reading_data](https://www.tensorflow.org/versions/master/how_tos/reading_data)[Accessed: 16/12/2015].
[[20]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref20) _Github_, (2016) TensorFlow Book – Jordi Torres. [Online]. Available at:[https://github.com/jorditorresBCN/LibroTensorFlow/blob/master/input_data.py](https://github.com/jorditorresBCN/LibroTensorFlow/blob/master/input_data.py)[Accessed: 19/02/2016].
[[21]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref21) _Github_, (2016) Shawn Simister. [Online]. Available at: [https://gist.github.com/narphorium/d06b7ed234287e319f18](https://gist.github.com/narphorium/d06b7ed234287e319f18) [Accessed: 9/01/2016].
[[22]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref22) Wikipedia, (2016). Squared Euclidean distance. [Online]. Available at:[https://en.wikipedia.org/wiki/Euclidean_distance#Squared_Euclidean_distance](https://en.wikipedia.org/wiki/Euclidean_distance#Squared_Euclidean_distance)[Accessed: 9/01/2016].
[[23]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref23) _In my opinion, the level of explanation of each operation it’s enough for the purpose of this book._
[[24]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref24) TensorFlow, (2016) Python API. [online]. Available in: [https://www.tensorflow.org/versions/master/api_docs/index.html](https://www.tensorflow.org/versions/master/api_docs/index.html) [Accessed: 19/02/2016].
[[25]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref25)Actually “_” is like any other variable, but many Python users, by convention, we use it to discard results.
[[26]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref26) Github, (2016) TensorFlow Book – Jordi Torres. [online]. Available at: [https://github.com/jorditorresBCN/LibroTensorFlow](https://github.com/jorditorresBCN/LibroTensorFlow) [Accessed: 19/02/2016].
[[27]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref27) TensorFlow, (2016) Tutorial MNIST beginners. [online]. Available at:[https://www.tensorflow.org/versions/master/ tutorials/mnist/beginners](https://www.tensorflow.org/versions/master/%C2%A0tutorials/mnist/beginners)[Accessed: 16/12/2015].
[[28]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref28) Neural Networks and Deep Learning.[Michael Nielsen](http://michaelnielsen.org/). [online]. Available at: [http://neuralnetworksanddeeplearning.com/index.html](http://neuralnetworksanddeeplearning.com/index.html) [Accessed: 6/12/2015].
[[29]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref29) The MNIST database of handwritten digits.[online]. Available at:[http://yann.lecun.com/exdb/mnist](http://yann.lecun.com/exdb/mnist) [Accessed: 16/12/2015].
[[30]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref30) Wikipedia, (2016). Antialiasing [online]. Available at: [https://en.wikipedia.org/wiki/Antialiasing](https://en.wikipedia.org/wiki/Antialiasing)[Accessed: 9/01/2016].
[[31]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref31)_ Github_, (2016) Book TensorFlow – Jordi Torres. [online]. Available at:[https://github.com/jorditorresBCN/LibroTensorFlow/blob/master/input_data.py](https://github.com/jorditorresBCN/LibroTensorFlow/blob/master/input_data.py) [Accessed: 9/01/2016].
[[32]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref32) Google (2016) TensorFlow. [online]. Available at: [https://tensorflow.googlesource.com](https://tensorflow.googlesource.com/)[Accessed: 9/01/2016].
[[33]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref33) Wikipedia, (2016). Sigmoid function [online]. Avaliable at: [https://en.wikipedia.org/wiki/Sigmoid_function](https://en.wikipedia.org/wiki/Sigmoid_function) [Accessed: 12/01/2016].
[[34]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref34) Wikipedia, (2016). Softmax function [online]. Available at: [https://en.wikipedia.org/wiki/Softmax_function](https://en.wikipedia.org/wiki/Softmax_function) [Accessed: 2/01/2016].
[[35]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref35) TensorFlow, (2016) Tutorial MNIST beginners. [online]. Available at:[https://www.tensorflow.org/versions/master/tutorials/mnist/beginners](https://www.tensorflow.org/versions/master/tutorials/mnist/beginners)[Accessed: 16/12/2015].
[[36]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref36) Neural Networks & Deep Learning.[Michael Nielsen](http://michaelnielsen.org/). [online]. Available at:[http://neuralnetworksanddeeplearning.com/index.html](http://neuralnetworksanddeeplearning.com/index.html)[Accessed: 6/12/2015].
[[37]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref37) TensorFlow Github: tensorflow/tensorflow/python/ops/gradients.py [Online]. Available at:[https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/ops/gradients.py](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/ops/gradients.py)[Accessed: 16/03/2016].
[[38]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref38)_ Github_, (2016) Libro TensorFlow – Jordi Torres. [online]. Available at:[https://github.com/jorditorresBCN/LibroTensorFlow](https://github.com/jorditorresBCN/LibroTensorFlow)[Accessed: 9/01/2016].
[[39]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref39) The reader can read more about the details of these parameters on the course website of CS231 –_Convolutional Neural Networks for Visual Recognition_(2015) [online]. Available at:[http://cs231n.github.io/convolutional-networks](http://cs231n.github.io/convolutional-networks)[Accessed: 30/12/2015].
[[40]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref40) GIMP –_Image processing software by GNU,_Convlution matrix documentation available at:[https://docs.gimp.org/es/plug-in-convmatrix.html](https://docs.gimp.org/es/plug-in-convmatrix.html)[Accessed: 5/1/2016].
[[41]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref41) TensorFlow, (2016_) Tutorials: Deep MNIST for experts_. [on line]. Availbile at:[https://www.tensorflow.org/versions/master/tutorials/mnist/pros/index.html](https://www.tensorflow.org/versions/master/tutorials/mnist/pros/index.html) [Consulted on: 2/1/2016]
[[42]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref42) TensorFlow, (2016)_Python API. ADAM Optimizer_[on líne]. Available at:[https://www.tensorflow.org/versions/master/ api_docs/python/train.html#AdamOptimizer](https://www.tensorflow.org/versions/master/%C2%A0api_docs/python/train.html#AdamOptimizer)[Accessed: 2/1/2016].
[[43]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref43) _Github_, (2016) Source code of this book [on líne]. Availible at: [https://github.com/jorditorresBCN/TutorialTensorFlow](https://github.com/jorditorresBCN/TutorialTensorFlow) [Consulted on: 29/12/2015].
[[44]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref44) TensorFlow, (2016) GPU-related issues. [online]. Available at: [https://www.tensorflow.org/versions/master/get_started/os_setup.html#gpu-related-issues](https://www.tensorflow.org/versions/master/get_started/os_setup.html#gpu-related-issues)[Accessed: 16/12/2015].
[[45]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref45) This output is result of using a server with 4 Tesla K40 GPUs from the[Barcelona Supercomputing Center (BSC-CNS)](http://www.bsc.es/).
[[46]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref46)_ Github_(2016) AymericDamien. [online]. Available at: [https://github.com/aymericdamien/TensorFlow-Examples](https://github.com/aymericdamien/TensorFlow-Examples) [Accessed: 9/1/2015].
[[47]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref47) Distributed TensorFlow, (2016) [online]. Available at: [https://github.com/tensorflow/tensorflow/tree/master/tensorflow/core/distributed_runtime](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/core/distributed_runtime)[Accessed: 16/12/2015].
[[48]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref48) _Github_, (2016) Source code of this book [on líne]. Availible at: [https://github.com/jorditorresBCN/TutorialTensorFlow](https://github.com/jorditorresBCN/TutorialTensorFlow) [Consulted on: 29/12/2015].
[[49]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref49) Twitter (11/11/2015). Kyle McDonald:_2010-2014: new deep learning toolkit is released every 47 days.__2015: every 22 days._[Online]. Available at:[https://twitter.com/kcimc/status/664217437840257024](https://twitter.com/kcimc/status/664217437840257024)[Accessed: 9/01/2016].
[[50]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref50) _GitHub,_(2016)_Awesome Deep Learning_. [Online]. Available at: [https://github.com/ChristosChristofidis/awesome-deep-learning](https://github.com/ChristosChristofidis/awesome-deep-learning)[Accessed: 9/01/2016].
[[51]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref51) Explore GitHub, Machine learning: [Online]. Available at:[https://github.com/showcases/machine-learning](https://github.com/showcases/machine-learning) [Accessed on: 2/01/2016]
[[52]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref52) Scikit-Learn GitHub: [Online]. Available at:[https://github.com/scikit-learn/scikit-learn](https://github.com/scikit-learn/scikit-learn)[Accessed: 2/3/2016]
[[53]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref53) Tensorflow/skflow GitHub: [Online]. Available at:[https://github.com/tensorflow/skflow](https://github.com/tensorflow/skflow)[Accessed: 2/1/2016]
[[54]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref54) Yann LeCun, Yoshua Bengio and Geoffrey Hinton (2015). “Deep Learning”. Nature 521: 436–444 doi:10.1038/nature14539. Available at:[http://www.nature.com/nature/journal/v521/n7553/full/nature14539.html](http://www.nature.com/nature/journal/v521/n7553/full/nature14539.html) [Accessed: 16/03/2016].
[[55]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref55) TensorFlow, (2016) Tutorial – Recurrent Neural Networks [Online]. Available at:[https://www.tensorflow.org/versions/r0.7/tutorials/recurrent/index.html](https://www.tensorflow.org/versions/r0.7/tutorials/recurrent/index.html)[Accessed: 16/03/2016].
[[56]](https://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#_ftnref56) Hello World en TensorFlow. Spanish version of this book [Online]. Available at:[https://jorditorres.org/libro-hello-world-en-tensorflow/](https://jorditorres.org/libro-hello-world-en-tensorflow/)[Accessed: 16/03/2016].
- TensorFlow 1.x 深度学习秘籍
- 零、前言
- 一、TensorFlow 简介
- 二、回归
- 三、神经网络:感知器
- 四、卷积神经网络
- 五、高级卷积神经网络
- 六、循环神经网络
- 七、无监督学习
- 八、自编码器
- 九、强化学习
- 十、移动计算
- 十一、生成模型和 CapsNet
- 十二、分布式 TensorFlow 和云深度学习
- 十三、AutoML 和学习如何学习(元学习)
- 十四、TensorFlow 处理单元
- 使用 TensorFlow 构建机器学习项目中文版
- 一、探索和转换数据
- 二、聚类
- 三、线性回归
- 四、逻辑回归
- 五、简单的前馈神经网络
- 六、卷积神经网络
- 七、循环神经网络和 LSTM
- 八、深度神经网络
- 九、大规模运行模型 -- GPU 和服务
- 十、库安装和其他提示
- TensorFlow 深度学习中文第二版
- 一、人工神经网络
- 二、TensorFlow v1.6 的新功能是什么?
- 三、实现前馈神经网络
- 四、CNN 实战
- 五、使用 TensorFlow 实现自编码器
- 六、RNN 和梯度消失或爆炸问题
- 七、TensorFlow GPU 配置
- 八、TFLearn
- 九、使用协同过滤的电影推荐
- 十、OpenAI Gym
- TensorFlow 深度学习实战指南中文版
- 一、入门
- 二、深度神经网络
- 三、卷积神经网络
- 四、循环神经网络介绍
- 五、总结
- 精通 TensorFlow 1.x
- 一、TensorFlow 101
- 二、TensorFlow 的高级库
- 三、Keras 101
- 四、TensorFlow 中的经典机器学习
- 五、TensorFlow 和 Keras 中的神经网络和 MLP
- 六、TensorFlow 和 Keras 中的 RNN
- 七、TensorFlow 和 Keras 中的用于时间序列数据的 RNN
- 八、TensorFlow 和 Keras 中的用于文本数据的 RNN
- 九、TensorFlow 和 Keras 中的 CNN
- 十、TensorFlow 和 Keras 中的自编码器
- 十一、TF 服务:生产中的 TensorFlow 模型
- 十二、迁移学习和预训练模型
- 十三、深度强化学习
- 十四、生成对抗网络
- 十五、TensorFlow 集群的分布式模型
- 十六、移动和嵌入式平台上的 TensorFlow 模型
- 十七、R 中的 TensorFlow 和 Keras
- 十八、调试 TensorFlow 模型
- 十九、张量处理单元
- TensorFlow 机器学习秘籍中文第二版
- 一、TensorFlow 入门
- 二、TensorFlow 的方式
- 三、线性回归
- 四、支持向量机
- 五、最近邻方法
- 六、神经网络
- 七、自然语言处理
- 八、卷积神经网络
- 九、循环神经网络
- 十、将 TensorFlow 投入生产
- 十一、更多 TensorFlow
- 与 TensorFlow 的初次接触
- 前言
- 1. TensorFlow 基础知识
- 2. TensorFlow 中的线性回归
- 3. TensorFlow 中的聚类
- 4. TensorFlow 中的单层神经网络
- 5. TensorFlow 中的多层神经网络
- 6. 并行
- 后记
- TensorFlow 学习指南
- 一、基础
- 二、线性模型
- 三、学习
- 四、分布式
- TensorFlow Rager 教程
- 一、如何使用 TensorFlow Eager 构建简单的神经网络
- 二、在 Eager 模式中使用指标
- 三、如何保存和恢复训练模型
- 四、文本序列到 TFRecords
- 五、如何将原始图片数据转换为 TFRecords
- 六、如何使用 TensorFlow Eager 从 TFRecords 批量读取数据
- 七、使用 TensorFlow Eager 构建用于情感识别的卷积神经网络(CNN)
- 八、用于 TensorFlow Eager 序列分类的动态循坏神经网络
- 九、用于 TensorFlow Eager 时间序列回归的递归神经网络
- TensorFlow 高效编程
- 图嵌入综述:问题,技术与应用
- 一、引言
- 三、图嵌入的问题设定
- 四、图嵌入技术
- 基于边重构的优化问题
- 应用
- 基于深度学习的推荐系统:综述和新视角
- 引言
- 基于深度学习的推荐:最先进的技术
- 基于卷积神经网络的推荐
- 关于卷积神经网络我们理解了什么
- 第1章概论
- 第2章多层网络
- 2.1.4生成对抗网络
- 2.2.1最近ConvNets演变中的关键架构
- 2.2.2走向ConvNet不变性
- 2.3时空卷积网络
- 第3章了解ConvNets构建块
- 3.2整改
- 3.3规范化
- 3.4汇集
- 第四章现状
- 4.2打开问题
- 参考
- 机器学习超级复习笔记
- Python 迁移学习实用指南
- 零、前言
- 一、机器学习基础
- 二、深度学习基础
- 三、了解深度学习架构
- 四、迁移学习基础
- 五、释放迁移学习的力量
- 六、图像识别与分类
- 七、文本文件分类
- 八、音频事件识别与分类
- 九、DeepDream
- 十、自动图像字幕生成器
- 十一、图像着色
- 面向计算机视觉的深度学习
- 零、前言
- 一、入门
- 二、图像分类
- 三、图像检索
- 四、对象检测
- 五、语义分割
- 六、相似性学习
- 七、图像字幕
- 八、生成模型
- 九、视频分类
- 十、部署
- 深度学习快速参考
- 零、前言
- 一、深度学习的基础
- 二、使用深度学习解决回归问题
- 三、使用 TensorBoard 监控网络训练
- 四、使用深度学习解决二分类问题
- 五、使用 Keras 解决多分类问题
- 六、超参数优化
- 七、从头开始训练 CNN
- 八、将预训练的 CNN 用于迁移学习
- 九、从头开始训练 RNN
- 十、使用词嵌入从头开始训练 LSTM
- 十一、训练 Seq2Seq 模型
- 十二、深度强化学习
- 十三、生成对抗网络
- TensorFlow 2.0 快速入门指南
- 零、前言
- 第 1 部分:TensorFlow 2.00 Alpha 简介
- 一、TensorFlow 2 简介
- 二、Keras:TensorFlow 2 的高级 API
- 三、TensorFlow 2 和 ANN 技术
- 第 2 部分:TensorFlow 2.00 Alpha 中的监督和无监督学习
- 四、TensorFlow 2 和监督机器学习
- 五、TensorFlow 2 和无监督学习
- 第 3 部分:TensorFlow 2.00 Alpha 的神经网络应用
- 六、使用 TensorFlow 2 识别图像
- 七、TensorFlow 2 和神经风格迁移
- 八、TensorFlow 2 和循环神经网络
- 九、TensorFlow 估计器和 TensorFlow HUB
- 十、从 tf1.12 转换为 tf2
- TensorFlow 入门
- 零、前言
- 一、TensorFlow 基本概念
- 二、TensorFlow 数学运算
- 三、机器学习入门
- 四、神经网络简介
- 五、深度学习
- 六、TensorFlow GPU 编程和服务
- TensorFlow 卷积神经网络实用指南
- 零、前言
- 一、TensorFlow 的设置和介绍
- 二、深度学习和卷积神经网络
- 三、TensorFlow 中的图像分类
- 四、目标检测与分割
- 五、VGG,Inception,ResNet 和 MobileNets
- 六、自编码器,变分自编码器和生成对抗网络
- 七、迁移学习
- 八、机器学习最佳实践和故障排除
- 九、大规模训练
- 十、参考文献