Skip to content


Subversion checkout URL

You can clone with
Download ZIP
A demonstration of how to use hash kernels for ridiculously unprincipled machine learning
Branch: master
Failed to load latest commit information.
scikit-learn @ bb7da14 Initial commit
.gitmodules Specify the number of salts to use in learning on FB data Treat floats as continous features
sklearn Initial commit

Hash kernels are a method of representing very large sparse feature vectors. But with a little imagination, they can serve as a way to represent just about any kind of feature.


Machine learning datasets obtained from the UCI Machine Learning Repository made experimenting with hash kernels incredibly easy. Details:

Frank, A. & Asuncion, A. (2010). UCI Machine Learning Repository []. Irvine, CA: University of California, School of Information and Computer Science.

Dataset URLs:

Something went wrong with that request. Please try again.