https://github.com/dongjunlee/deeplearning-notebooks
Deep Learning Notebooks Implements by TensorFlow, Python + numpy
https://github.com/dongjunlee/deeplearning-notebooks
deep-learning deeplearning-notebooks notebook python tensorflow tutorial
Last synced: 10 months ago
JSON representation
Deep Learning Notebooks Implements by TensorFlow, Python + numpy
- Host: GitHub
- URL: https://github.com/dongjunlee/deeplearning-notebooks
- Owner: DongjunLee
- Created: 2016-04-16T17:56:02.000Z (almost 10 years ago)
- Default Branch: master
- Last Pushed: 2017-05-03T09:24:48.000Z (over 8 years ago)
- Last Synced: 2025-04-15T00:13:40.984Z (10 months ago)
- Topics: deep-learning, deeplearning-notebooks, notebook, python, tensorflow, tutorial
- Language: Jupyter Notebook
- Homepage:
- Size: 1.38 MB
- Stars: 12
- Watchers: 2
- Forks: 3
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# DeepLearning Notebooks
These are deep learning examples implemented by TensorFlow, Python with Numpy.
## Prerequisites
All python code are base on python3 and use jupyter notebook.
- TensorFlow 1.0
- Scikit Learn
- matplotlib, Seaborn
- Numpy
- Pandas
## DataSet
1. [Boston Housing DataSet](https://archive.ics.uci.edu/ml/datasets/Housing)
2. [Mnist](http://yann.lecun.com/exdb/mnist/)
3. [CIFAR-10](https://www.cs.toronto.edu/~kriz/cifar.html)
4. [iris](http://archive.ics.uci.edu/ml/datasets/Iris)
5. [polarity dataset v2.0i (Movie Review)](http://www.cs.cornell.edu/people/pabo/movie-review-data/)
## Contents
**Python**, **TensorFlow** is minimal version.
**Exercise** is used model that mimicking scikit-learn's interface (fit, predict, etc...) and extended version from minimal.
1. Linear Regression
[ **Python** ](1.Linear_Regression/Python.ipynb)
|
[ **TensorFlow** ](1.Linear_Regression/TensorFlow.ipynb)
|
[ **Exercise** - Boston Housing(TensorFlow) ](1.Linear_Regression/Exercise-Boston_Housing_Problem(TensorFlow).ipynb)
2. Logistic Regression
[ **TensorFlow** ](2.Logistic_Regression/TensorFlow.ipynb)
|
[ **Exercies** - Iris(Python) ](2.Logistic_Regression/Iris(Python).ipynb)
3. Neural Network
- Two Layer Network:
[ **Python**) ](3.Neural_Network/Mnist(Python).ipynb)
|
[ AND, OR, XOR(Python)-2_Layer ](3.Neural_Network/AND,OR,XOR(Python)-2_Layer.ipynb)
- N Layer Network:
[ **Exercise** - AND, OR, XOR(Python)-N_Layer ](3.Neural_Network/AND,OR,XOR(Python)-N_Layer.ipynb),
[ **TensorFlow** ](3.Neural_Network/TensorFlow.ipynb)
4. Convolutional Neural Network
[ **TensorFlow**(AlexNet) ](4.Convolution_Network/TensorFlow.ipynb)
5. Recurrent Neural Network
[ **TensorFlow** ](5.Recurrent_Neuarl_Network/Tensorflow-RNN.ipynb)
6. Word2Vec
[ **TensorFlow** ](6.Word2Vec/TensorFlow-Word2Vec_Basic.ipynb)
7. CNN for Sentence Classification
[ **PDF** ](http://aclweb.org/anthology/D/D14/D14-1181.pdf)
|
[ **TensorFlow** ](7.TextCNN/TensorFlow-TextCNN.ipynb)
8. Char-RNN (a character-level language model to generate character sequences)
[ **TensorFlow**(Obama-RNN) ](8.CharRNN/TensorFlow-Char-RNN.ipynb)
9. Seq2Seq
[ **TensorFlow** ](9.Seq2Seq/TensorFlow.ipynb)
10. Adversarial Neural Cryptography
[ **TensorFlow** ](10.Adversarial_Neural_Cryptography/TensorFlow.ipynb)
## Reference
- [CS231n Convolutional Neural Networks for Visual Recognition](http://cs231n.github.io/)
- [CS224d: Deep Learning for Natural Language Processing](http://cs224d.stanford.edu/)
- [TensorFlow Tutorial](https://www.tensorflow.org/tutorials/)
- [WILDML](http://www.wildml.com/)
- [R2RT](http://r2rt.com/)