Course - Uncertainty in Deep Learning MT25

Created: October 09, 2025 | Updated: November 20, 2025 | Read markdown | About these notes | View in context | Study these flashcards

---

• Course webpage (Moodle)
• Lecture notes (old)
  • 1+2, Introduction and Bayesian probability theory
  • 3+4, Bayesian probabilistic modelling
  • 5+6, Uncertainty over functions and approximate inference
  • 7+8, Mathematical tools and stochastic approximate inference
  • 9+10, Classification in Bayesian neural networks and uncertainty in classification
• Lecture videos
  • 2024-2025
  • 2025-2026
• Practicals (useful resources)
  • Week 4, Setting a baseline
  • Week 5, A toolkit for the probabilistic machine learner
  • Week 6, Playing with uncertainties
  • Week 7&8, What does my model know?
• Additional references
  • Bayesian epistemology
  • Gaussians recap
  • Oxford Applied and Theoretical Machine Learning Group
  • “Probabilistic Machine Learning: An Introduction” by Kevin Murphy
  • “Probabilistic Machine Learning: Advanced Topics” by Kevin Murphy
  • “Uncertainty in Deep Learning”, Prof. Yarin Gal’s dissertation
• Other courses this term: Courses MT25^U

Notes

• Notes - Uncertainty in Deep Learning MT25, Probability reference^U
• Notes - Uncertainty in Deep Learning MT25, Statistics reference^U
• Notes - Uncertainty in Deep Learning MT25, Kullback-Leibler divergence^U

Lectures

• Lecture - Uncertainty in Deep Learning MT25, Introduction^U
• Notes - Uncertainty in Deep Learning MT25, Bayesian probability theory^U
• Lecture - Uncertainty in Deep Learning MT25, Bayesian probabilistic modelling^U
• Lecture - Uncertainty in Deep Learning MT25, Bayesian probabilistic modelling of functions^U
• Lecture - Uncertainty in Deep Learning MT25, Uncertainty over functions^U
• Lecture - Uncertainty in Deep Learning MT25, Approximate inference^U
• Lecture - Uncertainty in Deep Learning MT25, Some very useful mathematical tools^U
• Lecture - Uncertainty in Deep Learning MT25, Stochastic approximate inference in DNNs^U
• redacted^?
• redacted^?

Related Notes

• Course - Probability^U
• Course - Machine Learning MT23^U
  • Notes - Machine Learning MT23, Bayesian machine learning^U

Problem Sheets

To-Do List

---

Related posts

• Lecture - Uncertainty in Deep Learning MT25, Some very useful mathematical tools^U

  (incoming)
• Lecture - Uncertainty in Deep Learning MT25, Introduction^U

  (incoming)
• Lecture - Uncertainty in Deep Learning MT25, Stochastic approximate inference in DNNs^U

  (incoming)
• Lecture - Uncertainty in Deep Learning MT25, Bayesian probabilistic modelling of functions^U

  (incoming)
• Lecture - Uncertainty in Deep Learning MT25, Uncertainty over functions^U

  (incoming)
• Lecture - Uncertainty in Deep Learning MT25, Bayesian probabilistic modelling^U

  (incoming)
• Lecture - Uncertainty in Deep Learning MT25, Approximate inference^U

  (incoming)
• Notes - Uncertainty in Deep Learning MT25, Statistics reference^U

  (incoming)
• Notes - Uncertainty in Deep Learning MT25, Kullback-Leibler divergence^U

  (incoming)
• Part C^U

  (incoming)
• University Notes^U

  (incoming)
• Courses MT25^U

  (incoming)
• Course - Geometric Deep Learning HT26^U

  (incoming)
• Course - Theories of Deep Learning MT25^U

  (incoming)
• Notes - Machine Learning MT23, Bayesian machine learning^U

  (incoming)
• Lecture - Machine Learning MT23, VII^U

  (sim: 0.685)
• Lecture - Machine Learning MT23, II^U

  (sim: 0.661)
• Notes - Uncertainty in Deep Learning MT25, Probability reference^U

  (incoming)