Associate Professor in Machine Learning

Porting Sparse Filtering from numpy to tensorflow

less than 1 minute read

Published:

Sparse filtering is a recently-developed unsupervised feature distribution lerning algorithm with interesting properties. Basic implementations are available in Matlab, and python relying on the numpy library. In this post we explain and analyze a re-implementation of the python code in order to work within the tensorflow framework.

Running SF with the tensorflow backend allows for greater flexibility and customizability in exchange for computational cost. While the original SF relies on an efficient quasi-Newton optimization algorithm that requires explicit knowledge of the derivative, the new version exploits the feature of automatic differentiation of the tensorflow framework for optimization opening the way for the quick development of novel feature distribution learning algorithms.

Notebook here

You May Also Enjoy

Reviewing Consistencies

less than 1 minute read

Published:

In previous posts we have discussed theoretical and conceptual properties of abstractions between causal models, while at the same time implementing code for checking our statements and for running simulations.

Scenarios of Confounding

less than 1 minute read

Published:

Causality and causal inference deal with expressing and reasoning about relationships of cause and effects, and structural causal model provide a rigorous formalism to assess causality.