Probabilistic Machine Learning and AI
How can a machine learn from experience? Probabilistic modelling provides a mathematical framework for understanding what learning is, and has therefore emerged as one of the principal approaches for designing computer algorithms that learn from data acquired through experience. The field of machine learning underpins recent advances in artificial intelligence, and data science, and has the potential to play an important role in scientific data analysis. I will highlight some current areas of research at the frontiers of machine learning, including our project on developing an Automatic Statistician.
- Séries:
- Cambridge Lab PhD Summer School
- Date:
- Haut-parleurs:
- Zoubin Ghahramani
- Affiliation:
- University of Cambridge and Uber AI Labs
-
-
Scarlet Schwiderski-Grosche
Director
-
-
Taille: Cambridge Lab PhD Summer School
-
The Malmo Collaborative AI Challenge
Speakers:- Scarlet Schwiderski-Grosche
-
Counterfactual Multi-Agent Policy Gradients
Speakers:- Scarlet Schwiderski-Grosche
-
Design - On the Human Side
Speakers:- Alex Taylor,
- Scarlet Schwiderski-Grosche
-
Probabilistic Machine Learning and AI
Speakers:- Scarlet Schwiderski-Grosche
-
Policy Gradient Methods: Tutorial and New Frontiers
Speakers:- Scarlet Schwiderski-Grosche
-
Strategic Thinking for Researchers
Speakers:- Andy Gordon,
- Jeff Running
-
How to Write a Great Research Paper
Speakers:- Scarlet Schwiderski-Grosche,
- Simon Peyton Jones
-
Project Malmo – a platform for fundamental AI research
Speakers:- Scarlet Schwiderski-Grosche
-
No Compromises: Distributed Transactions with Consistency, Availability, and Performance
Speakers:- Scarlet Schwiderski-Grosche
-
The Evolution of Innovation
Speakers:- Scarlet Schwiderski-Grosche
-
How to Give a Great Research Talk
Speakers:- Scarlet Schwiderski-Grosche,
- Simon Peyton Jones