Difference between revisions of "Generative AI"
| Line 20: | Line 20: | ||
** [[Autoencoder (AE) / Encoder-Decoder]] | ** [[Autoencoder (AE) / Encoder-Decoder]] | ||
** Sequence Models | ** Sequence Models | ||
| + | *** [[Transformer]] | ||
*** [[Recurrent Neural Network (RNN)]] | *** [[Recurrent Neural Network (RNN)]] | ||
*** [[Sequence to Sequence (Seq2Seq)]] | *** [[Sequence to Sequence (Seq2Seq)]] | ||
Revision as of 07:03, 2 October 2019
YouTube search... ...Google search
- machines learn to perceive their surroundings by training only on data obtained by themselves
- AI Solver
- Generative Query Network (GQN)
- Discriminative vs. Generative
- Natural Language Generation (NLG)
- Generative model | Wikipedia
- Synthetic Labeling
- Three main types:
- Autoencoder (AE) / Encoder-Decoder
- Sequence Models
- Adversarial Networks
Generative modeling asks how likely it is, given condition X, that you’ll observe outcome Y. The approach has proved incredibly potent and versatile. How Artificial Intelligence Is Changing Science | Dan Falk - Quanta Magazine
Deep Generative Modeling
Agents
Generative Modeling Language