Machine Learning With Statistical And Causal Methods
Last Updated on September 5, 2016
In November 2014, Bernhard Scholkopf was awarded the Milner Award by the Royal Society for his contributions to machine learning.
In accepting the award, he gave a layman’s presentation of his work on statistical and causal machine learning methods titled “Statistical and causal approaches to machine learning“.
It’s an excellent one hour talk and I highly recommend that you watch it.
Statistical Learning
On the statistical side, Scholkopf talks about empirical inference and generalisation.
An interesting and motivating point he makes early is on hard inference problems, motivating his work on kernel machines.
Specifically, he references the problem of classifying DNA sequences from locations as mentioned in Sonnenburg, et al. 2008 titled “Large Scale Multiple Kernel Learning“. In the paper, the authors show that algorithm performance increases as a function of the amount of data available.
The Need For Big Data
Graph taken from Large Scale Multiple Kernel Learning
He calls this a paradigm changing
To finish reading, please visit source site