Deep Autoencoders For Collaborative Filtering – Towards Data Science

An Autoencoder is a deep learning neural network architecture that achieves state of the art performance in the area of collaborative filtering. In the first part of the article I will give you a theoretical overview and basic mathematics behind simple Autoencoders and their extension the Deep Autoencoders. In the second part we will dive in the practical stuff and I will show you how to implement this technique in TensorFlow step by step. In this article I will include and comment only the most important parts of the model. The whole model, the input pipeline and the preprocessing can be viewed in the corresponding GitHub repository.