Difference between revisions of "Tutorial: TensorFlow References"
(→Intro to Machine Learning and TensorFlow, Google video) |
(→Introduction for Beginners with No Background) |
||
| (24 intermediate revisions by the same user not shown) | |||
| Line 5: | Line 5: | ||
This page contains resources that will help you get up to speed with Machine Learning and TensorFlow. I have attempted to list the resources in a logical order, so that if you start from scratch, you will be presented by increasingly more sophisticated concepts as you progress. Note that all these tutorials assume a good understanding of Python an of how to install various packages for Python. | This page contains resources that will help you get up to speed with Machine Learning and TensorFlow. I have attempted to list the resources in a logical order, so that if you start from scratch, you will be presented by increasingly more sophisticated concepts as you progress. Note that all these tutorials assume a good understanding of Python an of how to install various packages for Python. | ||
<br /> | <br /> | ||
| + | ==Introduction for Beginners with No Background== | ||
| + | <br /> | ||
| + | This is by far the best video I found on illustrating how neural nets work. Don't miss it! The first 15 minutes are the core of the information. | ||
| + | <br /> | ||
| + | <videoflash>aircAruvnKk</videoflash> | ||
| + | <br /> | ||
| + | |||
| + | ==Understanding Deep Learning== | ||
| + | <br /> | ||
| + | * [https://medium.com/towards-data-science/april-edition-towards-deep-learning-aa2a81e48185 12 Articles to better understand deep learning], in the April 2017 edition of ''Towards Deep Learning''. Each article averages a 6-minute read. | ||
| + | <br /> | ||
| + | |||
==Understanding Deep Neural Nets== | ==Understanding Deep Neural Nets== | ||
[[Image:TensorFlowPlayGround.png|500px|right]] | [[Image:TensorFlowPlayGround.png|500px|right]] | ||
| − | * Start with this [http://blogs.scientificamerican.com/sa-visual/unveiling-the-hidden-layers-of-deep-learning/ article from Scientific American]: [http://blogs.scientificamerican.com/sa-visual/unveiling-the-hidden-layers-of-deep-learning/ Unveiling the Hidden Layers of Deep Learning, by Amanda Montanez, editor at Scientific American]. This short article references [http://www.scientificamerican.com/article/springtime-for-ai-the-rise-of-deep-learning/ Springtime for AI, the rise of deep-learning], published by Scientific American (you'll need a subscription to access this article.) | + | * '''Step 1''':Start with this [http://blogs.scientificamerican.com/sa-visual/unveiling-the-hidden-layers-of-deep-learning/ article from Scientific American]: [http://blogs.scientificamerican.com/sa-visual/unveiling-the-hidden-layers-of-deep-learning/ Unveiling the Hidden Layers of Deep Learning, by Amanda Montanez, editor at Scientific American]. This short article references [http://www.scientificamerican.com/article/springtime-for-ai-the-rise-of-deep-learning/ Springtime for AI, the rise of deep-learning], published by Scientific American (you'll need a subscription to access this article.) |
<br /> | <br /> | ||
| − | * '''Play | + | * '''Step 2''': ''Play'' with the [http://playground.tensorflow.org/#activation=relu&batchSize=21&dataset=spiral®Dataset=reg-plane&learningRate=0.03®ularizationRate=0&noise=10&networkShape=3,3,2&seed=0.56096&showTestData=true&discretize=true&percTrainData=70&x=false&y=true&xTimesY=true&xSquared=true&ySquared=false&cosX=false&sinX=true&cosY=false&sinY=true&collectStats=false&problem=classification&initZero=false TensorFlow playground], created by Daniel Smilkov and Shan Carter. |
<br /> | <br /> | ||
<br /> | <br /> | ||
| Line 18: | Line 30: | ||
<br /> | <br /> | ||
<br /> | <br /> | ||
| + | |||
==Machine-Learning Recipes== | ==Machine-Learning Recipes== | ||
<br /> | <br /> | ||
| Line 41: | Line 54: | ||
<br /> | <br /> | ||
| + | |||
| + | ==Soon Hin Khor's Gentlest Introduction to TensorFlow== | ||
<br /> | <br /> | ||
| + | Soon Hin Khor's [https://medium.com/all-of-us-are-belong-to-machines/the-gentlest-introduction-to-tensorflow-248dc871a224#.25a26txrt introduction] is a good place to start with TensorFlow, looking at a simple linear model for the price of houses as a function of size. | ||
<br /> | <br /> | ||
| + | ==[http://bcomposes.com/2015/11/26/simple-end-to-end-tensorflow-examples/ Jason Baldridge's Tutorial]== | ||
<br /> | <br /> | ||
| + | Posted on November 26, 2015, this [http://bcomposes.com/2015/11/26/simple-end-to-end-tensorflow-examples/ post] is another interesting exploration of TensorFlow that starts from scratch and provides the code for working examples. | ||
<br /> | <br /> | ||
| + | |||
| + | ==[http://www.cs.toronto.edu/~frossard/about/ David Frossard's Tutorials]== | ||
<br /> | <br /> | ||
| − | + | {| | |
| + | | | ||
| + | A very good, clean, stylish [http://www.cs.toronto.edu/~frossard/post/multiple_linear_regression/ tutorial on multiple linear regression using TensorFlow]. | ||
| + | | | ||
| + | [[Image:FrossardTensorBoardImage.png|right|350px]] | ||
| + | |} | ||
<br /> | <br /> | ||
| Line 63: | Line 88: | ||
After a 10-minute pause (which is part of the video), the next speaker starts with a Jupyter notebook exploring various aspects of the wine-quality data. The notebook and associated data are available from this [https://github.com/PythonWorkshop/intro-to-tensorflow github repository]. | After a 10-minute pause (which is part of the video), the next speaker starts with a Jupyter notebook exploring various aspects of the wine-quality data. The notebook and associated data are available from this [https://github.com/PythonWorkshop/intro-to-tensorflow github repository]. | ||
| + | <br /> | ||
| + | |||
| + | <br /> | ||
<br /> | <br /> | ||
==WILDML: A Convolutional Neural Net for Text Classification in TF== | ==WILDML: A Convolutional Neural Net for Text Classification in TF== | ||
<br /> | <br /> | ||
* [http://www.wildml.com/2015/12/implementing-a-cnn-for-text-classification-in-tensorflow/ WildML Tutorial]: A very detailed tutorial on text classification using TensorFlow. | * [http://www.wildml.com/2015/12/implementing-a-cnn-for-text-classification-in-tensorflow/ WildML Tutorial]: A very detailed tutorial on text classification using TensorFlow. | ||
| + | <br /> | ||
| + | <br /> | ||
| + | ==RNNs== | ||
| + | <br /> | ||
| + | * [http://www.wildml.com/2016/08/rnns-in-tensorflow-a-practical-guide-and-undocumented-features/ Practical Guide to RNNs with Tensorflow, by WildML] | ||
| + | * [http://colah.github.io/posts/2015-08-Understanding-LSTMs/ Understanding Long Short Term Memory (LTSM) Networks], by Colah. | ||
| + | * [http://monik.in/a-noobs-guide-to-implementing-rnn-lstm-using-tensorflow/ A Noobs Guide to RNN-LSTM], by Monik Pachema. | ||
| + | * [https://gist.github.com/monikkinom/e97d518fe02a79177b081c028a83ec1c Monik Pachema's github repository] | ||
| + | * [https://arxiv.org/pdf/1503.04069.pdf LSTM: A Search Space Odyssey], by Greff et al. | ||
| + | * [http://karpathy.github.io/2015/05/21/rnn-effectiveness/ The Unreasonable Effectiveness of RNNs], by Andrej Karpathy. | ||
| + | * [https://medium.com/towards-data-science/lstm-by-example-using-tensorflow-feb0c1968537 LSTM Using Tensorflow], an good article, clear and well written, by Rowel Atienza, of the University of the Philippines-Diliman.<br /> | ||
| + | * [http://yoavz.com/music_rnn/ Music Language Modeling with Recurrent Neural Networks], by Yoav Zimmerman, with his full report available [http://yoavz.com/music_rnn_paper.pdf here]. | ||
| + | <br /> | ||
| + | <br /> | ||
| + | <br /> | ||
| + | <br /> | ||
| + | <br /> | ||
<br /> | <br /> | ||
[[Category:Tutorials]][[Category:TensorFlow]] | [[Category:Tutorials]][[Category:TensorFlow]] | ||
Latest revision as of 16:14, 22 October 2017
--D. Thiebaut (talk) 12:00, 6 August 2016 (EDT)
Contents
- 1 References & Tutorials
- 1.1 Introduction for Beginners with No Background
- 1.2 Understanding Deep Learning
- 1.3 Understanding Deep Neural Nets
- 1.4 Machine-Learning Recipes
- 1.5 Soon Hin Khor's Gentlest Introduction to TensorFlow
- 1.6 Jason Baldridge's Tutorial
- 1.7 David Frossard's Tutorials
- 1.8 Intro to Machine Learning and TensorFlow, Google video
- 1.9 WILDML: A Convolutional Neural Net for Text Classification in TF
- 1.10 RNNs
References & Tutorials
This page contains resources that will help you get up to speed with Machine Learning and TensorFlow. I have attempted to list the resources in a logical order, so that if you start from scratch, you will be presented by increasingly more sophisticated concepts as you progress. Note that all these tutorials assume a good understanding of Python an of how to install various packages for Python.
Introduction for Beginners with No Background
This is by far the best video I found on illustrating how neural nets work. Don't miss it! The first 15 minutes are the core of the information.
Understanding Deep Learning
- 12 Articles to better understand deep learning, in the April 2017 edition of Towards Deep Learning. Each article averages a 6-minute read.
Understanding Deep Neural Nets
- Step 1:Start with this article from Scientific American: Unveiling the Hidden Layers of Deep Learning, by Amanda Montanez, editor at Scientific American. This short article references Springtime for AI, the rise of deep-learning, published by Scientific American (you'll need a subscription to access this article.)
- Step 2: Play with the TensorFlow playground, created by Daniel Smilkov and Shan Carter.
Machine-Learning Recipes
A very good (though quick) introduction to various Machine Learning concepts, presented by Josh Gordon. It is highly recommended to code all the examples presented.
Machine Learning Recipe #1: Hello world!
Machine Learning Recipe #2: Decision Trees
Machine Learning Recipe #3: What makes a good feature?
Machine Learning Recipe #4: Pipeline
Machine Learning Recipe #5: Writing your own classifier
Soon Hin Khor's Gentlest Introduction to TensorFlow
Soon Hin Khor's introduction is a good place to start with TensorFlow, looking at a simple linear model for the price of houses as a function of size.
Jason Baldridge's Tutorial
Posted on November 26, 2015, this post is another interesting exploration of TensorFlow that starts from scratch and provides the code for working examples.
David Frossard's Tutorials
|
A very good, clean, stylish tutorial on multiple linear regression using TensorFlow. |
 |
Intro to Machine Learning and TensorFlow, Google video
This is a very good approach to TensorFlow which uses the wine quality data-set from UC Irvine Machine Learning repository. It uses the red wine data (winequality-red.csv). It starts with a 30-minute math tutorial presented by jenhsin0@gmail.com, and it covers
- entropy,
- variable dependency,
- dimensionality reduction,
- graph representation of models,
- activation functions in neural nets,
- loss functions, and
- gradient descent.
After a 10-minute pause (which is part of the video), the next speaker starts with a Jupyter notebook exploring various aspects of the wine-quality data. The notebook and associated data are available from this github repository.
WILDML: A Convolutional Neural Net for Text Classification in TF
- WildML Tutorial: A very detailed tutorial on text classification using TensorFlow.
RNNs
- Practical Guide to RNNs with Tensorflow, by WildML
- Understanding Long Short Term Memory (LTSM) Networks, by Colah.
- A Noobs Guide to RNN-LSTM, by Monik Pachema.
- Monik Pachema's github repository
- LSTM: A Search Space Odyssey, by Greff et al.
- The Unreasonable Effectiveness of RNNs, by Andrej Karpathy.
- LSTM Using Tensorflow, an good article, clear and well written, by Rowel Atienza, of the University of the Philippines-Diliman.
- Music Language Modeling with Recurrent Neural Networks, by Yoav Zimmerman, with his full report available here.
