Recently I worked on a paper by Hao Wang, Collaborative Deep learning for Recommender Systems; which uses a two way tightly coupled method, Collaborative filtering for Item correlation and Stacked Denoising Autoencoders for the Optimization of the problem.

I want to know the limitations of using stacked Autoencoders and Hierarchical Bayesian methods to Recommender systems.


A good recommender program is one of the hardest problems in AI. Recomender needs to first know me (by talking to me or by analyzing the movies that I graded as good). Then it needs to be able to recognize similarity of my taste to a new movie. So it needs to watch movies that I liked, build a list of common things between these movies and then watch 100 random new movies and pick the one that has the most patterns in common with my liked movies.

So once again a good similarity recognition system is the key to successfull AI.

| improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.