Translations:Neural Networks/28/en: Difference between revisions
(Importing a new version from external source) |
(Importing a new version from external source) Tag: Manual revert |
||
| Line 1: | Line 1: | ||
* '''[[Convolutional Neural Networks]]''' (CNNs) — designed for grid-structured data such as images, using local connectivity and weight sharing. | * '''[[Convolutional Neural Networks]]''' (CNNs) — designed for grid-structured data such as images, using local connectivity and weight sharing. | ||
* '''[[Recurrent Neural Networks]]''' (RNNs) — designed for sequential data, with connections that form cycles to maintain hidden state. | * '''[[Recurrent Neural Networks]]''' (RNNs) — designed for sequential data, with connections that form cycles to maintain hidden state. | ||
* ''' | * '''Transformers''' — attention-based architectures that have become dominant in natural language processing and increasingly in vision. | ||
* '''Autoencoders''' — networks trained to reconstruct their input, used for dimensionality reduction and generative modelling. | * '''Autoencoders''' — networks trained to reconstruct their input, used for dimensionality reduction and generative modelling. | ||
* '''Generative adversarial networks''' (GANs) — pairs of networks (generator and discriminator) trained in competition to generate realistic data. | * '''Generative adversarial networks''' (GANs) — pairs of networks (generator and discriminator) trained in competition to generate realistic data. | ||
Revision as of 22:01, 27 April 2026
- Convolutional Neural Networks (CNNs) — designed for grid-structured data such as images, using local connectivity and weight sharing.
- Recurrent Neural Networks (RNNs) — designed for sequential data, with connections that form cycles to maintain hidden state.
- Transformers — attention-based architectures that have become dominant in natural language processing and increasingly in vision.
- Autoencoders — networks trained to reconstruct their input, used for dimensionality reduction and generative modelling.
- Generative adversarial networks (GANs) — pairs of networks (generator and discriminator) trained in competition to generate realistic data.