A Restricted Boltzmann Machine (RBM) is a probabilistic graphical model used for unsupervised learning. RBMs help discover hidden structures in data, making them suitable for applications like video recommendation systems.
An RBM consists of two layers:

Visible Layer: This layer receives the input data.
Hidden Layer: This layer represents features or classifications derived from the input data.

Every node in the visible layer connects to every node in the hidden layer, but there are no connections within the same layer. This characteristic makes it "restricted." The connections have weights representing the probability of nodes being active.
RBMs learn by adjusting weights and biases through two phases:

Feed Forward Pass: Input data is multiplied by weights and added to bias values in the hidden layer, identifying positive and negative associations between visible and hidden units.
Feed Backwards Pass: This phase adjusts weights, biases, and logs probabilities to refine the network's understanding of data patterns.

By training with enough data, RBMs learn the probability distribution across the dataset and can predict relationships between visible and hidden features.
Video Recommendation Example:
In a video recommendation system, the visible layer can represent videos watched by a user. The hidden layer can represent video categories (like machine learning or Python programming) or video styles (demo, vlog, etc.). The RBM learns the probability of a user who likes machine learning videos also liking Python videos.
Other Applications:
RBMs can be used for feature extraction and pattern recognition tasks, including:

Understanding handwritten text
Identifying structures in datasets

RBMs offer a powerful way to analyze data without manually adjusting weights and iterating through nodes.

https://youtu.be/L3ynnRgpZwg?si=wdiaU_9o1WF1iqzr

Ver todos los episodios