Advanced · Neural Networks
Boltzmann machine
Visual diagram · (in preparation) · Math · (in preparation) · Worked example · 3 difficulty levels.
TL;DR. A type of stochastic recurrent neural network used for generative learning and optimization.
Technical Definition
A type of stochastic recurrent neural network used for generative learning and optimization.
How it works
A Boltzmann machine is a stochastic recurrent neural network that can learn a distribution over its input data. It's characterized by its units, which can be turned on or off probabilistically, and its symmetric connections. Boltzmann machines are generative models and are related to Hopfield networks but allow for hidden units and stochasticity.
Related Concepts
- Neural Network — A computing system inspired by biological neural networks that learns patterns from data through interconnected layers of nodes.
- Generative model — A type of machine learning model that can create new data instances similar to the data it was trained on, or estimate the likelihood of a given data point originating from the training distribution.