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.

Recommendations with deep neural networks

Recommendations with deep neural networks - Python Tutorial

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

Start my 1-month free trial Buy for my team

Recommendations with deep neural networks

“

- [Instructor] So let's go back to Spider and if you still have the contents of the deep learning folder opened up you should be able to select the autoreq.py file. There it is. Like our RBM example our implementation of using an auto encoder for recommendations uses Tensor Flow and it's structured in much the same way. As a reminder, an auto encoder is just a three layer neural network with an input layer, a hidden layer, and an output layer. Learning the weights between the input and hidden layer is called encoding and reconstructing predictions with the weights between the hidden layer and the output layer is called decoding. But fundamentally it's just a neural network with one hidden layer. Let's skip to the neural net function here. That's where things are fundamentally different from the RBM example. It's not too complicated. You can see we're setting up the weights for the encoding and decoding here…

Contents