From the course: Building Recommender Systems with Machine Learning and AI

Unlock this course with a free trial

Join today to access over 23,200 courses taught by industry experts.

Auto-encoders for recommendations: Deep learning for recs

Auto-encoders for recommendations: Deep learning for recs - Python Tutorial

From the course: Building Recommender Systems with Machine Learning and AI

Start my 1-month free trial Buy for my team

Auto-encoders for recommendations: Deep learning for recs

“

- [Instructor] We mentioned that restricted Boltzmann machines were a very early type of neural network. And the field of deep learning has evolved considerably since then. What happens if we apply a more contemporary neural network to the problem? Well, as we'll see, it's possible, but not without its challenges. People started using deeper neural networks for recommender systems in 2015, which seems pretty recent. But it's a long time in the context of current AI research. A group from the Australian National University published a paper called AutoRec: Autoencoders Meet Collaborative Filtering and they used the topology you see here. It looks a lot more familiar to the sorts of networks we covered in our introduction to deep learning. You have three layers: an input layer on the bottom that contains individual ratings, a hidden layer, and an output layer that gives us our predictions. A matrix of weights between the layers is maintained across every instance of this network, as…

Contents