5. Generative models
A generative model is an algorithm that generates samples according to the same probability law as the data provided in the initial database, but without this probability law necessarily being explicitly described.
5.1 Variable autoencoders
We have seen how deep learning methods can be used to perform dimensionality reduction using auto-encoders by associating with each object xi in a very high-dimensional space a latent representation hi = fθ(x), where fθ is a neural network, and by optimizing the parameters θ of fθ and of a second neural network ...
Exclusive to subscribers. 97% yet to be discovered!
Already subscribed? Log in!
Generative models
Conclusion
Bibliography
Exclusive to subscribers. 97% yet to be discovered!
Already subscribed? Log in!
Article included in this offer
"Technological innovations"
(
201 articles
)
Updated and enriched with articles validated by our scientific committees
A set of exclusive tools to complement the resources
