Text full multimedia monochrome

First time here?

Find out more about how The Lecture List works.

Coronavirus situation update

Our lecture organisers may or may not have had time to update their events with cancellation notices. Clearly social gatherings are to be avoided and that includes lectures. STAY AT HOME FOLKS, PLEASE.


Find out what you can do to keep The Lecture List online

Microsoft Distinguished Research Lecture

Toward Causal Machine Learning

Microsoft Distinguished Research Lecture: Toward Causal Machine Learning

Speaker: Bernhard Schölkopf

In machine learning, we use data to automatically find dependences in the world, with the goal of predicting future observations. Most machine learning methods build on statistics, but one can also try to go beyond this, assaying causal structures underlying statistical dependences. Can such causal knowledge help prediction in machine learning tasks? We argue that this is indeed the case, due to the fact that causal models are more robust to changes that occur in real world datasets. We touch upon the implications of causal models for machine learning tasks such as domain adaptation, transfer learning, and semi-supervised learning. We also present an application to the removal of systematic errors for the purpose of exoplanet detection.

Machine learning currently mainly focuses on relatively well-studied statistical methods. Some of the causal problems are conceptually harder, however, the causal point of view can provide additional insights that have substantial potential for data analysis.


Prof. Dr. Bernhard Schölkopf | talks | www


Date and Time:

15 May 2015 at 4:45 pm


1 hour



Microsoft Research
21 Station Road

More at Microsoft Research...




Available from:

Please register for this talk to ensure your place: http://research.microsoft.com/en-us/events/msdrl/tcml.aspx

Additional Information:

Please contact msrcenq@microsoft.com for more information.

Register to tell a friend about this lecture.


If you would like to comment about this lecture, please register here.


Any ad revenue is entirely reinvested into the Lecture List's operating fund