Deep Probabilistic Modelling with Gaussian Processes - Neil D. Lawrence - NIPS Tutorial 2017
Neil Lawrence is a Professor of Machine Learning at the University of Sheffield, but he is currently on leave at Amazon where he is a Director of Machine Learning and founder of Amazon Research Cambridge.
Neural network models are algorithmically simple, but mathematically complex. Gaussian process models are mathematically simple, but algorithmically complex. In this tutorial we will explore Deep Gaussian Process models. They bring advantages in their mathematical simplicity but are challenging in their algorithmic complexity. We will give an overview of Gaussian processes and highlight the algorithmic approximations that allow us to stack Gaussian process models: they are based on variational methods. In the last part of the tutorial will explore a use case exemplar: uncertainty quantification. We end with open questions.
Видео Deep Probabilistic Modelling with Gaussian Processes - Neil D. Lawrence - NIPS Tutorial 2017 канала The Artificial Intelligence Channel
Neural network models are algorithmically simple, but mathematically complex. Gaussian process models are mathematically simple, but algorithmically complex. In this tutorial we will explore Deep Gaussian Process models. They bring advantages in their mathematical simplicity but are challenging in their algorithmic complexity. We will give an overview of Gaussian processes and highlight the algorithmic approximations that allow us to stack Gaussian process models: they are based on variational methods. In the last part of the tutorial will explore a use case exemplar: uncertainty quantification. We end with open questions.
Видео Deep Probabilistic Modelling with Gaussian Processes - Neil D. Lawrence - NIPS Tutorial 2017 канала The Artificial Intelligence Channel
Показать
Комментарии отсутствуют
Информация о видео
10 декабря 2017 г. 20:00:01
02:01:24
Другие видео канала
"Is Bayesian deep learning the most brilliant thing ever?" - a panel discussionML Tutorial: Gaussian Processes (Richard Turner)Probabilistic Machine Learning - Prof. Zoubin GhahramaniLiving together: Mind and machine intelligence | Neil Lawrence | TEDxExeterSalonHistory of Bayesian Neural Networks (Keynote talk)Neil Lawrence - Gaussian Processes Part 110 Reasons to Get Off Social Media - Jaron LanierYuval Harari - The Challenges of The 21st CenturyA (very) Brief History of Carl Friedrich GaussEM algorithm: how it worksDeep Learning Basics: Introduction and OverviewGaussian Processes: Their Power and Limitations, Dr. Vinesh Maguire-Rajpaul (Cambridge Univ.)Quantum Deep LearningGaussian Processes with Neil LawrencePanel: What can Quantum do for AI?What is Quantum Machine Learning? - Quantum Computing TutorialDeep and Multi-fidelity learning with Gaussian processes: Andreas Damianou, AmazonDebatiendo sobre inteligencia artificialVincent Warmerdam: Winning with Simple, even Linear, Models | PyData London 2018