# lectures-labs

**Repository Path**: mirrors_lepy/lectures-labs

## Basic Information

- **Project Name**: lectures-labs
- **Description**: Slides and Jupyter notebooks for the Deep Learning lectures at M2 Data Science Université Paris Saclay
- **Primary Language**: Unknown
- **License**: MIT
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2020-09-25
- **Last Updated**: 2025-07-02

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Deep Learning course: lecture slides and lab notebooks

This course is being taught at as part of [Master Datascience Paris
Saclay](http://datascience-x-master-paris-saclay.fr)

<p style="text-align: center">
<a href="http://datascience-x-master-paris-saclay.fr/"><img
  src="slides/04_conv_nets_2/images/Logo_Master_Datascience.png" width="300"/></a>
</p>

## Table of contents

The course covers the basics of Deep Learning, with a focus on applications.

### Lecture slides

  - [Neural Networks and Backpropagation](https://m2dsupsdlclass.github.io/lectures-labs/slides/01_intro_to_deep_learning/index.html)
  - [Embeddings and Recommender Systems](https://m2dsupsdlclass.github.io/lectures-labs/slides/02_recommender_systems/index.html)
  - [Convolutional Neural Networks for Image Classification](https://m2dsupsdlclass.github.io/lectures-labs/slides/03_conv_nets/index.html)
  - [Deep Learning for Object Dection and Image Segmentation](https://m2dsupsdlclass.github.io/lectures-labs/slides/04_conv_nets_2/index.html)
  - [Recurrent Neural Networks and NLP](https://m2dsupsdlclass.github.io/lectures-labs/slides/05_deep_nlp/index.html)
  - [Expressivity, Optimization and Generalization](https://m2dsupsdlclass.github.io/lectures-labs/slides/06_expressivity_optimization_generalization/index.html)

Note: press "P" to display the presenter's notes that include some comments and
additional references.

### Lab and Home Assignment Notebooks

The Jupyter notebooks for the labs can be found in the `labs` folder of
the [github repository](https://github.com/m2dsupsdlclass/lectures-labs/):

    git clone https://github.com/m2dsupsdlclass/lectures-labs

**WARNING**: these notebooks only work with `tensorflow==0.12.1 keras==1.2.2`.
Please follow the [installation\_instructions.md](
https://github.com/m2dsupsdlclass/lectures-labs/blob/master/installation_instructions.md)
to get started.

Direct links to the rendered notebooks including solutions:

#### Lab 1: Neural Networks and Backpropagation

  - [Intro to MLP with Keras, Numpy and TensorFlow](https://github.com/m2dsupsdlclass/lectures-labs/blob/master/labs/01_backprop/Intro_MLP_keras_numpy_tensorflow_rendered.ipynb)

#### Lab 2: Embeddings and Recommender Systems

  - [Short Intro to Embeddings with Keras](https://github.com/m2dsupsdlclass/lectures-labs/blob/master/labs/02_neural_recsys/Short_Intro_to_Embeddings_with_Keras_rendered.ipynb)
  - [Neural Recommender Systems with Explicit Feedback](https://github.com/m2dsupsdlclass/lectures-labs/blob/master/labs/02_neural_recsys/Explicit_Feedback_Neural_Recommender_System_rendered.ipynb)
  - [Neural Recommender Systems with Implicit Feedback and the Triplet Loss](https://github.com/m2dsupsdlclass/lectures-labs/blob/master/labs/02_neural_recsys/Implicit_Feedback_Recsys_with_the_triplet_loss_rendered.ipynb)

#### Lab 3: Convolutional Neural Networks for Image Classification

  - [Convolution and ConvNets with TensorFlow](https://github.com/m2dsupsdlclass/lectures-labs/blob/master/labs/03_conv_nets/ConvNets_with_TensorFlow_rendered.ipynb)
  - [Pretrained ConvNets with Keras](https://github.com/m2dsupsdlclass/lectures-labs/blob/master/labs/03_conv_nets/Pretrained_ConvNets_with_Keras_rendered.ipynb)
  - [Fine Tuning a pretrained ConvNet with Keras (GPU required)](https://github.com/m2dsupsdlclass/lectures-labs/blob/master/labs/03_conv_nets/Fine_Tuning_Deep_CNNs_with_GPU_rendered.ipynb)

#### Lab 4: Deep Learning for Object Dection and Image Segmentation

  - [Fully Convolutional Neural Networks](https://github.com/m2dsupsdlclass/lectures-labs/blob/master/labs/04_conv_nets_2/Fully_Convolutional_Neural_Networks_rendered.ipynb)
  - [ConvNets for Classification and Localization](https://github.com/m2dsupsdlclass/lectures-labs/blob/master/labs/04_conv_nets_2/ConvNets_for_Classification_and_Localization_rendered.ipynb)

#### Lab 5: Text Classification, Word Embeddings and Language Models

  - [Text Classification and Word Vectors](https://github.com/m2dsupsdlclass/lectures-labs/blob/master/labs/05_deep_nlp/NLP_word_vectors_classification_rendered.ipynb)
  - [Character Level Language Model (GPU required)](https://github.com/m2dsupsdlclass/lectures-labs/blob/master/labs/05_deep_nlp/Character_Level_Language_Model_rendered.ipynb)

#### Lab 6: Sequence to Sequence for Machine Translation

  - [Translation of Numeric Phrases with Seq2Seq](https://github.com/m2dsupsdlclass/lectures-labs/blob/master/labs/06_seq2seq/Translation_of_Numeric_Phrases_with_Seq2Seq_rendered.ipynb)

## Acknowledgments

This lecture is built and maintained by Olivier Grisel and Charles Ollion

Charles Ollion, head of research at [Heuritech](http://www.heuritech.com) -
Olivier Grisel, software engineer at
[Inria](https://team.inria.fr/parietal/en)

<a href="http://www.heuritech.com"><img src="slides/04_conv_nets_2/images/logo heuritech v2.png"
width="300"/></a> <a href="https://team.inria.fr/parietal/en"><img
src="slides/04_conv_nets_2/images/inria-logo.png" width="250"/></a>

We thank the  Orange-Keyrus-Thalès chair for supporting this class.

## License

All the code in this repository is made available under the MIT license
unless otherwise noted.

The slides are published under the terms of the [CC-By 4.0
license](https://creativecommons.org/licenses/by/4.0/).