Nordic Probabilistic AI School
The ProbAI school is here to provide an inclusive education environment serving state-of-the-art expertise in machine learning and artificial intelligence.
Praktische info:
Inschrijven?
- Inschrijvingen: tot 27 mrt. 2022
- Prijs: (Doctoraats)studenten → 250 EUR; Academici → 500 EUR; Industrie → 1000 EUR
georganiseerd door:
Leertraject
Objective
Our objective is to bring an intermediate to advanced level “summer” school with a focus on probabilistic machine learning. We cover topics such as probabilistic models, variational approximations, deep generative models, latent variable models, normalizing flows, neural ODEs, probabilistic programming, and much more.
Concept
We intend to provide an efficient and quality knowledge transfer through:
- carefully designed curriculum and program,
- coordination between our lecturers,
- a mix of theoretical lectures and hands-on tutorials,
- support for students from our teaching assistants,
- fostering close interaction and collaboration between students, lecturers and teaching assistants.
All that in a friendly and inclusive environment that we will co-create, together. Read our Code of Conduct.
Topics
The above program will be structured into theoretical lectures and hands-on tutorials with the following modules:
- Probabilistic models, variational inference and probabilistic programming (Day 1 to Day 2)
- Introduction to probabilistic modeling
- Bayesian modeling: prior, likelihood and posterior
- Concepts of Bayesian networks and latent-variable models
- Posterior inference and parameter learning
- Modeling techniques
- Variational inference
- Mean-field, CAVI and conjugate models
- Stochastic Variational Inference and Optimization
- Black-box variational inference
- Automatic Differentiation Variational inference
- Probabilistic programming
- Introduction to the concept of probabilistic programming
- Language syntax and semantics
- Inference mechanisms
- Introduction to probabilistic modeling
- Deep Generative Models (Day 3 to Day 5)
- Variational Auto-Encoders
- Generative Adversarial Networks
- Normalizing Flows
- ODEs and Bayesian Neural Nets
- Simulation-Based Inference
- Bayesian Neural Networks
- Gaussian Processes
Note: The described modules provide a non-exhaustive list of covered topics.
Gerelateerde opleidingen
