We can turn a simple autoencoder into something sophisticated. Autoencoders discover a latent mapping z, which as a lower-dimensional representation of the input x, can be useful for pre-training networks and creating recommender models. However, how autoencoders compress information may come in millions of ways. To truly polish how z can be generated, we turn […]
Autoencoders are a simple neural network approach to recommendation
A tutorial to create a recommender pipeline with Kedro and MLFlow.
This is part 2 of my talk on recommenders. The presentation describes the intuitions of matrix factorization and how to implement it in R. I delivered this in the R-Users Group PH meetup group this November. If you wish to see some more recommender material in this blog, check this out:
Join me in this roadtrip of different recommender algorithms.
Hey all, it’s time for another machine learning blog. This time, I’m tackling recommendation systems. I’ve found this neat dataset, Steam Video games over at Kaggle. You should definitely check it out. We’ll be going from analyzing how people play these games, to how we can infer ratings from usage patterns. I’ll be implementing my […]