Simplicial Complex Networks

no code implementations • ICLR 2020 • Mohammad Firouzi, Sadra Boreiri, Hamed Firouzi

Universal approximation property of neural networks is one of the motivations to use these models in various real-world problems.

regression Topological Data Analysis

KF-LAX: Kronecker-factored curvature estimation for control variate optimization in reinforcement learning

no code implementations • 11 Dec 2018 • Mohammad Firouzi

A key challenge for gradient based optimization methods in model-free reinforcement learning is to develop an approach that is sample efficient and has low variance.

Atari Games reinforcement-learning +1

Extracting Implicit Social Relation for Social Recommendation Techniques in User Rating Prediction

no code implementations • 5 Dec 2016 • Seyed Mohammad Taheri, Hamidreza Mahyar, Mohammad Firouzi, Elahe Ghalebi K., Radu Grosu, Ali Movaghar

Hence, we build our method, called Hell-TrustSVD, on top of the state-of-the-art social recommendation technique to incorporate both the extracted implicit social relations and ratings given by users on the prediction of items for an active user.

Recommendation Systems Relation +1