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.
Tuning restricted Boltzmann machines - Python Tutorial
From the course: Building Recommender Systems with Machine Learning and AI
Tuning restricted Boltzmann machines
- So here's your challenge, see if we just have the wrong topology and parameters for our RBM. The right number of hit nodes, the right learning rates, the right bat size, and the right number of epochs needed to converge, all depend on the amount and the nature of our training data. So there is no single correct answers for RBMs in general. It's your job to tune the RBM for the data that we have. So give it a go, as we did before use SurpriseLib's grid search CV class, and pick a couple of hyper-parameters to work with. Keep trying different sets of values, using the results each time to converge on a better set of values to try next time. Until you have parameters that yield the best results. I'd encourage you to write this from scratch, if you're up for it, but you may notice that my solution is already in your course materials as the RBMtuning.py file. If you choose to cheat and just use my code, it's still a worthwhile exercise. As most of the work here is just the process of…
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.
Contents
-
-
-
-
-
-
-
-
-
-
(Locked)
Intro to deep learning for recommenders2m 19s
-
(Locked)
Restricted Boltzmann machines (RBMs)8m 2s
-
(Locked)
Recommendations with RBMs, part 112m 46s
-
Recommendations with RBMs, part 27m 11s
-
(Locked)
Evaluating the RBM recommender3m 44s
-
(Locked)
Tuning restricted Boltzmann machines1m 43s
-
(Locked)
Exercise results: Tuning a RBM recommender1m 15s
-
(Locked)
Auto-encoders for recommendations: Deep learning for recs4m 27s
-
(Locked)
Recommendations with deep neural networks7m 23s
-
(Locked)
Clickstream recommendations with RNNs7m 23s
-
(Locked)
Get GRU4Rec working on your desktop2m 42s
-
(Locked)
Exercise results: GRU4Rec in action7m 51s
-
(Locked)
Bleeding edge alert: Deep factorization machines5m 49s
-
(Locked)
More emerging tech to watch5m 14s
-
(Locked)
-
-
-
-
-