Autoencoder

Matrix (chemical analysis)

Deep learning

Machine learning

Physics

Non-negative matrix factorization

Pattern recognition (psychology)

Artificial intelligence

Eigenvalues and eigenvectors

Composite material

Materials science

Collaborative filtering

MovieLens

Computer science

Matrix decomposition

Recommender system

Quantum mechanics

This paper proposes AutoRec, a novel autoencoder framework for collaborative filtering (CF). Empirically, AutoRec's compact and efficiently trainable model outperforms state-of-the-art CF techniques (biased matrix factorization, RBM-CF and LLORMA) on the Movielens and Netflix datasets.

AutoRec