How do I train a neural-network for a recommendation system?_问答_开发者

How do I train a neural-network for a recommendation system?

开发者 https://www.devze.com 2023-01-04 00:51 出处：网络

I\'ve set up an ANN with back-propagation as a book recommendation system. I only have one hidden layer in the network, and both the input and the output layers are books, since you should be able t

I've set up an ANN with back-propagation as a book recommendation system.

I only have one hidden layer in the network, and both the input and the output layers are books, since you should be able to enter a book and receive more book recommendations.

I already have a lot of data about users and their ratings (1 to 5) for books. I'd like to get it into the neural net开发者_如何学JAVAwork (set up all the weights) for this data without having to go through the back-propagation process. Do it somehow more mechanically.

Say each user has about 100 rated books in their library, how do I set the weights for them? How do the books in the user's library relate to the other books in the user's library?

Thanks.

So it sounds like you don't want to use a neural network. I have found that neural networks are more difficult and take longer to train in these types of sparse feature spaces. You want to predict (I believe) books that a person might like given their ratings and the ratings of people who made similar purchases.

You should look at collaborative filtering. I am not saying that you can't solve the problem with neural networks but I am not sure that you want would really want to.

I agree that you probably dont't want to use a neural network.

Usually with ANNs, the initial weights are assigned random values (maybe calculated through a random number algorithm) after which they are optimised through the training iterations.

Have you looked into Fuzzy Logic theories to solve your problem? Based on my experience, it sounds like fuzzy logic may be suited to this system where the book ratings can be used as membership functions to determine which category/book to recommend.

Neural Networks are not a solution to your problem. What you need is some metric of similarity between two books. This could include some tagging mechanism, or Dewey Classification System. Then, the user's recommendation should include the books that are more relevant to the ones he likes.