In this project, we will take a look at how to use embeddings to create a book recommendation system. Keras is used to create an embedding model as it makes it easy to create neural network embeddings as well as working with multiple inputs and output layers. For simplicity reasons, I didn’t add any fully-connected layers at the end, even though this could have increased the accuracy by quite a bit. If you want a more accurate model this is something to try out. Embeddings are visualized by reducing the dimensions using PCA and TSNE.
divensambhwani / book-recommendation--using-keras Goto Github PK
View Code? Open in Web Editor NEWBook recommendation system using embeddings.