gtshs2 / autorec Goto Github PK
View Code? Open in Web Editor NEWAutorec (Autoencoders Meet Collaborative Filtering)
Autorec (Autoencoders Meet Collaborative Filtering)
Hi!
I cannot understand a technical step. If only the weights related to the observed ratings are updated during backpropagation, this means that the weights related to the ratings of the test set will never be touched.
Is this not a network with extreme overfitting ?
How is it able to generalize ?
In test_model() method, you use below dictionary to feed model:
feed_dict={self.input_R: self.test_R, self.input_mask_R: self.test_mask_R}
so you feed model with test_R to predict test ratings! Isn't it wrong?I believe the feed_dict must be as below:
feed_dict={self.input_R: self.train_R, self.input_mask_R: self.test_mask_R}
so the model won't see test_R before predicting it.
May I know what the training error is in your case? When I plot it, the training error(RMSE) goes up while the testing error decreases.
Thanks
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.