M2MO: Modélisation Aléatoire, Finance et Data Science

Master en statistique, probabilités et finance - Université Paris 7 - Paris Diderot

 
 
 
 
 
 
Courses Group Data Science Deep learning
 
 

Deep learning

Lecturer: S. Gaiffas
Period: 
Term  3
ECTS: 3
Schedule: 2 hours of lecture  per week

Outline

  1. Introduction to Deep Learning
  2. Forward and backward propagation and solvers
  3. Embeddings, matrix factorization, factorization machines and recommender systems
  4. Convolutional neural networks for image classification
  5. Network architectures for object detection and image segmentation
  6. Recurrent neural networks, Long Short-Term Memory (LSTM) units for learning based on sequences
  7. Learning for sequences to sequences, attention and memory
  8. Unsupervised deep learning and generative models

Bibliographie

  • Goodfellow, I. and Bengio, Y., and Courville, A. (2016). Deep Learning. MIT Press.
  • Chollet, F. and Allaire, J. J. (2018). Deep Learning with R. Manning Pub.
  • Chollet, F. and Allaire, J. J. (2018). Deep Learning with Python. Manning Pub.