v2.11.0 (5518)

PA - C8 - DS-télécom-6 : Deep Learning 1


Deep Learning (machine learning based on deep arti cial neural
networks) has become extremely popular over the last years due to the
very good results it allows for regression, classi cation or generation.
The objective of this course is to cover the three main types of
networks (multi-layer-perceptron, recurrent-neural-network and con-
volutional neural network). This course range from the perceptron to
the generation of adversarial images.
Each lesson is followed by a corresponding lab where student learn
to implement these networks using the currently most popular frame-
works (tensor
ow, pytorch and keras).

1 Format
6 sessions of 3.5 hours + Exam
2 Teachers
Geo roy Peeters, Alasdair Newson (Telecom Paris)
3 Grading
30% labs/project, 70% written exam


Lectures content
Multi-Layer-Perceptron (MLP)
Perceptron, Logistic Regression, Chain rule, Back-propagation, Deep Neural Acti-
vation functions, Vanishing gradient, Initialization, Regularization (L1,L2,DropOut),
Alternative Gradient Descent, Batch-normalization

Recurrent Neural Network (RNN)
Simple RNN, Forward Propagation, Backward Propagation Through Time, Van-
ishing/ Exploding gradients, Gated Units (LSTM, GRU), Various architectures,
Sequence-to-sequence, Attention model

Convolutional Neural Network (CNN)
CNNs use sparse connectivity and weight sharing to reduce parameters and create
more powerful networks , connections are organized in a convolution operation,
CNNs now provide the state-of-the-art in a vast array of problems, we will see how
CNNs work and we will implement them for classi cation problems

 text recognition, sentiment classi cation
 generating music

image recognition
 image generation
Programming language
 Python (numpy, scikit-learn, matplotlib)
 DL frameworks: tensor
ow, pytorch, keras
 Use Telecom computers, your own labtop or colab.research.google.com !
needs a Google account ! open one before the rst Lab !
 a Graphics Processing Unit (GPU) will not be required, however if you have
one, this will speed up the learning process

Diplôme(s) concerné(s)

Format des notes

Numérique sur 20

Littérale/grade réduit

Pour les étudiants du diplôme Data Sciences

Le rattrapage est autorisé (Max entre les deux notes)
    L'UE est acquise si Note finale >= 10
    • Crédits ECTS acquis : 2.5 ECTS

    Programme détaillé

    4 Planning
    Date Type Content Teacher Location
    2019/09/19 PM Lesson MLP G. Peeters Paris (Amphi Estaunie)
    2019/09/26 PM Lab MLP G. Peeters, A. Newson + others Paris (C126, C127, C129, C130, 2019/10/03 PM Lesson RNN G. Peeters Paris (Amphi Estaunie)
    2019/10/10 PM Lab RNN G. Peeters, A. Newson + others Paris (C126, C127, C129, C130, 2019/10/24 PM Lesson CNN A. Newson Paris (Amphi Estaunie)
    2019/11/14 PM Lab CNN A. Newson, G. Peeters + others Saclay (1A201, 1A207, 1A226, 2019/11/21 PM Exam Saclay (Amphi OB01)

    Veuillez patienter