![[Search]](/static/images/search.gif){kind=small}
![[A-Z Index]](/static/images/az.gif){kind=small}
![[Contact]](/static/images/contact.gif){kind=small}
![[University of Cambridge]](/static/images/identifier2.gif){kind=small}
![[Talks.cam]](/static/images/talkslogosmall.gif)
Stanley Lazic, Cantab
Thursday 08 November 2018, 11:30-12:30
The Benefits of Bayesian Machine Learning
- 👤 Speaker: Stanley Lazic, Cantab
- 📅 Date & Time: Thursday 08 November 2018, 11:30 - 12:30
- 📍 Venue: Open Plan Area, BP Institute, Madingley Rise CB3 0EZ
Abstract
Bayesian predictive models (a.k.a model-based machine learning or probabilistic programming) have several advantages over classic machine learning methods, including the ability to incorporate and propagate all sources of uncertainty and to include external information. In addition, predictions and model outputs are easy to interpret and there are many ways to check the model and understand where it goes wrong. Surprisingly, cross-validation to tune hyperparameters is not required because hyperparameters can be learned from the data. The benefits of Bayesian ML will be discussed with examples from preclinical research in the pharmaceutical industry.
Series This talk is part of the Institute for Energy and Environmental Flows (IEEF) series.
Included in Lists
- All Talks (aka the CURE list)
- Cambridge Energy Seminars
- Department of Earth Sciences seminars
- history
- Institute for Energy and Environmental Flows (IEEF)
- MyList
- NanoDTC Energy Materials Talks
- Open Plan Area, BP Institute, Madingley Rise CB3 0EZ
- ps635
Note: Ex-directory lists are not shown.