This course equips students with a comprehensive foundation of modern deep learning, enabling students to design and train discriminative and generative neural networks for a wide range of tasks. Topics include:

• Deep learning applications (natural language processing, computer vision, audio processing, biology, robotics, science), principles and regulations
• Loss functions, data and labels, data provenance
• Training models: gradients and initialization
• Generalization and performance
• Transformers
• Graph neural networks
• Generative adversarial networks
• Variational autoencoders
• Diffusion models
• Multi-modal models
• Interpretability, explanations, bias and fairness

machine learning, neural networks, deep learning, python

• Basics in probabilities and statistics
• Linear algebra
• Differential calculus
• Python programming

• Basics in optimization
• Basics in algorithmic
• Basics in signal processing

Discrete and continuous distributions, normal density, law of large numbers, conditional probabilities, Bayes, PCA, vector, matrix operations, Euclidean spaces, Jacobian, Hessian, chain rule, notion of minima, gradient descent, computational costs, Fourier transform, convolution.

• Interpret the performance of a deep learning model
• Analyze the limitations of a deep learning model
• Justify the choices for training and testing a deep learning model
• Propose new solutions for a given application

• Respect relevant legal guidelines and ethical codes for the profession.
• Take account of the social and human dimensions of the engineering profession.
• Design and present a poster.
• Make an oral presentation.
• Demonstrate the capacity for critical thinking

Ex-cathedra lectures, class discussion, exercises (using python), group project.

Attendance to lectures, participation in discussions, completing exercises, completing a project, reading written material (scientific papers and books).

Excercises and group project.

• https://go.epfl.ch/EE-559https://go.epfl.ch/EE-559