Restricted Boltzmann Machines
Offered By: YouTube
Course Description
Overview
Restricted Boltzmann Machines (RBM) are a particular type of Gibbsian network or graphical model that is distinguished by having a layered structure with a hidden and a visible layer and by the fact that units within a layer are not connected to each other, which makes the units statistically independent given the other layer. RBMs can have many units and are often used to model high dimensional data, such as images.
Syllabus
RBM 1.1-1.3 - Restricted Boltzmann Machines (32 min).
RBM 1.4-1.7 - Restricted Boltzmann Machines (25 min).
Taught by
Prof. Laurenz Wiskott
Related Courses
Introduction to Linear Models and Matrix AlgebraHarvard University via edX Data Analysis for Life Sciences
Harvard University via edX Continuous Algorithms - Sampling and Optimization in High Dimension
Simons Institute via YouTube Recent Progress in Algorithmic Robust Statistics via the Sum-of-Squares Method
Simons Institute via YouTube Statistical Physics and Computation in High Dimension
Simons Institute via YouTube