This directory has a set of examples of how to build various kinds of recommender systems using MXNet. It also includes a set of tools for using sparse data.
The examples are driven by notebook files.
These examples use and demonstrate a number of layers and other tools that can be used outside of these examples. They are all available from the recotools
package.
NegativeSamplingDataIter
CosineLoss
CrossEntropyLoss
SparseRandomProjection
SparseBagOfWordProjection
Thanks to xlvector for the first Matrix Factorization example that provided the basis for these examples.