This course provides a simple introduction to Restricted Boltzmann Machines (RBM) and their training process through a real-life example involving people and pets. The learning outcomes include understanding RBM, training processes, contrastive divergence, Gibbs sampling, updating weights, and various sampling problems. The course teaches skills such as calculating scores and probabilities, as well as picking random samples with conditions. The teaching method involves a step-by-step explanation with practical examples. The intended audience for this course is beginners interested in machine learning concepts and applications.
Restricted Boltzmann Machines - A Friendly Introduction
Overview
Syllabus
Introduction:
Mystery:
Scores:
Probabilities:
Training
Contrastive Divergence:
Small Problem:
Gibbs Sampling:
Updating Weights:
Sampling Problems:
Independent Sampling:
Picking Random Samples with Conditions:
Picking Completely Random Samples:
Summary:
Conclusion:
Taught by
Serrano.Academy
