Deep Learning course: lecture slides and lab notebooks
This course is being taught at as part of Master Datascience Paris Saclay
Note: We're adding content to this lecture for early 2018, expect a few broken things in the notebooks and slides during this process
Table of contents
The course covers the basics of Deep Learning, with a focus on applications.
Lecture slides
- Neural Networks and Backpropagation
- Embeddings and Recommender Systems
- Convolutional Neural Networks for Image Classification
- Deep Learning for Object Detection and Image Segmentation
- Recurrent Neural Networks and NLP
- Expressivity, Optimization and Generalization
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:
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
to get started.
Direct links to the rendered notebooks including solutions:
Lab 1: Neural Networks and Backpropagation
Lab 2: Embeddings and Recommender Systems
- Short Intro to Embeddings with Keras
- Neural Recommender Systems with Explicit Feedback
- Neural Recommender Systems with Implicit Feedback and the Triplet Loss
Lab 3: Convolutional Neural Networks for Image Classification
- Convolution and ConvNets with TensorFlow
- Pretrained ConvNets with Keras
- Fine Tuning a pretrained ConvNet with Keras (GPU required)
Lab 4: Deep Learning for Object Dection and Image Segmentation
Lab 5: Text Classification, Word Embeddings and Language Models
Lab 6: Sequence to Sequence for Machine Translation
Acknowledgments
This lecture is built and maintained by Olivier Grisel and Charles Ollion
Charles Ollion, head of research at Heuritech - Olivier Grisel, software engineer at Inria
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.