Luigi Acerbi - Practical sample-efficient Bayesian inference for models with and without likelihoods

preview_player
Показать описание
Machine learning Coffee Seminar, 21st September 2020.

  1. Finnish Center for Artificial Intelligence FCAI
Рекомендации по теме
Luigi Acerbi - 0:47:36

Luigi Acerbi - Practical sample-efficient Bayesian inference for models with and without likelihoods

'Opening of ProbAI 0:17:11

'Opening of ProbAI 2022' by Luigi Acerbi

'Closing of ProbAI 0:08:00

'Closing of ProbAI 2022' by Luigi Acerbi

Martin Andraud: Accelerating 0:44:16

Martin Andraud: Accelerating various AI algorithms on the edge: from software to hardware challenges

Luigi Tizzano: Lecture 1:47:18

Luigi Tizzano: Lecture II

Quasi-Bayesian (QB) learning 0:05:30

Quasi-Bayesian (QB) learning - Benjamin Guedj (Spotlight session)

Judy Slee Seminar 0:28:42

Judy Slee Seminar Bayesian Graphical Models of Anxiety and Belief Updating in the Classic Beads Task

Geometric Sequences - 0:08:21

Geometric Sequences - Applying the Formula

Prof. Sethu Vijayakumar 0:54:49

Prof. Sethu Vijayakumar - Robots that Learn: Old Dreams, New Tools

MathSciNet for Early 0:58:12

MathSciNet for Early Career Mathematicians

2020 ECE641 - 0:52:52

2020 ECE641 - Lecture 06: Bayesian Estimation

University of Helsinki: 9:00:01

University of Helsinki: Mind and Matter Conference 16.6. - 18.6.2022 - Day 3

Roly Owers: A 0:54:40

Roly Owers: A Social License for Equestrian Sport

'Bayesian Neural Networks 2:50:51

'Bayesian Neural Networks (advanced)' by José Miguel Hernández–Lobato

Комментарии
Автор

Very fantastic work. I am seeking some efficient way to approximate Bayesian posterior distribution except MCMC. Your research inspired me a lot! I am just curious what do you mean 'not-too-complex' posterior distribution. Thanks!

jicezeng