From the course: Building Recommender Systems with Machine Learning and AI
Join today to access over 23,200 courses taught by industry experts.
Tune the hyperparameters on SVD - Python Tutorial
From the course: Building Recommender Systems with Machine Learning and AI
Tune the hyperparameters on SVD
- [Instructor] You can probably guess what your next exercise is. Go ahead and try this out. Modify the SVD bake off script such that I searches for the best hyperparameters to use with SVD. Then generate top end recommendations with it and see how they look. Oh, and if you notice that the SVDTuning.py file included in the course materials, yeah, that's the solution to this exercise. Resist the temptation to look at it unless you really get stuck. We'll review that file when we come back. So we can briefly take a look at our SVDTuning.py file here to see how I went about doing hyperparameter tuning on SVD. You'll see it's mainly the same code we covered in the slides to set up the GridSearchCV object and use it to find the best parameters to set on SVD. We then set up a little bake off between SVD using the default parameters, and the tune parameters we learned from GridSearchCV. Here we see the results. I settled on 20 epochs, a learning rate of .005 and 50 factors. You may have…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.