A Movie Recommender System using Restricted Boltzmann Machine (RBM), approach used is collaborative filtering.
A Movie Recommender System using Restricted Boltzmann Machine (RBM) approach used is collaborative filtering. This system is an algorithm that recommends items by trying to find users that are similar to each other based on their item ratings.
RBM is a Generative model with two layers(Visible and Hidden) that assigns a probability to each possible binary state vectors over its visible units. Visible layer nodes have visible bias(vb) and Hideen layer nodes have hidden bias(hb). A weight matrix of row length equal to input nodes and column length equal to output nodes.
The dataset used is MovieLens 1M Dataset acquired by Grouplens contains movies, users and movie ratings by these users.
Our model works in the following manner :-