Recommenders: Autoencoder models

[luiscastro193]

Have you considered adding models based on autoencoders? They look pretty interesting: https://arxiv.org/abs/1901.00415

[miguelgfierro]

Thanks for the suggestion Luis. We are in fact going to add this one https://github.com/miguelgfierro/sciblog_support/blob/master/Intro_to_Recommendation_Systems/Intro_Recommender.ipynb

[luiscastro193]

Awesome :)

[gramhagen]

this implementation also looks interesting: https://paperswithcode.com/paper/hybrid-recommender-system-based-on-autoe2

[miguelgfierro]

TODO:

compare results with old code movielens results:https://github.com/NVIDIA/DeepRecommender/issues/11

[miguelgfierro]

Initial result: https://github.com/microsoft/recommenders/blob/autoencoder/notebooks/02_model/deep_autoencoder_deep_dive.ipynb