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

Unlock this course with a free trial

Join today to access over 22,600 courses taught by industry experts.

Amazon DSSTNE

Amazon DSSTNE - Python Tutorial

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

Start my 1-month free trial Buy for my team

Amazon DSSTNE

“

- Next we're going to talk about a system from Amazon called DSSTNE. That stands for Deep Scalable Sparse Tensor Neural Engine. Back when I worked at Amazon's personalization team, our algorithms and systems were some of the most closely guarded secrets in the company. But in 2016, they open sourced DSSTNE, and published an article on exactly how to use it to produce recommendations at Amazon scale. DSSTNE makes it possible to set up deep neural networks using sparse data, like the ratings data we have when training recommender systems, without writing a single line of code. All you have to do is convert your training data into the format DSSTNE expects, write a short configuration file that defines the topology of the neural network you want and how it's optimized, and it does the rest. DSSTNE also runs on a GPU, and can process massive amounts of data very quickly. If your PC has multiple GPUs, it can even distribute the load across them, and compute recommendations in parallel. And…

Contents