Difference between revisions of "Generative AI"
m |
m |
||
| Line 5: | Line 5: | ||
|description=Helpful resources for your journey with artificial intelligence; videos, articles, techniques, courses, profiles, and tools | |description=Helpful resources for your journey with artificial intelligence; videos, articles, techniques, courses, profiles, and tools | ||
}} | }} | ||
| − | [ | + | [https://www.youtube.com/results?search_query=Generative+Modeling YouTube search...] |
| − | [ | + | [https://www.google.com/search?q=Generative+Modeling ...Google search] |
* [[AI Solver]] | * [[AI Solver]] | ||
| Line 13: | Line 13: | ||
* [[Natural Language Generation (NLG)]] | * [[Natural Language Generation (NLG)]] | ||
* [[Moonshots#Emergence from Analogies|Emergence from Analogies]] | * [[Moonshots#Emergence from Analogies|Emergence from Analogies]] | ||
| − | * [ | + | * [https://en.wikipedia.org/wiki/Generative_model Generative Model | Wikipedia] |
| − | * [[ | + | * [[Datsa Augmentation, Data Labeling, and Auto-Tagging#Synthetic Labeling|Synthetic Labeling]] |
* [https://stablediffusionweb.com/ Stable Diffusion | Stable Diffusion] ... a latent text-to-image diffusion model capable of generating photo-realistic images given any text input | * [https://stablediffusionweb.com/ Stable Diffusion | Stable Diffusion] ... a latent text-to-image diffusion model capable of generating photo-realistic images given any text input | ||
* Demos, generating... | * Demos, generating... | ||
| − | ** Music: [ | + | ** Music: [https://colab.research.google.com/notebooks/magenta/piano_transformer/piano_transformer.ipynb Generating Piano Music with Transformer | I. Simon, A. Huang, J. Engel, C. "Fjord" Hawthorne - Google on Colab] play with pretrained [[Transformer]] models for piano music generation, based on the [https://magenta.tensorflow.org/music-transformer Music Transformer model] |
| − | ** Faces: [ | + | ** Faces: [https://colab.research.google.com/github/tensorflow/hub/blob/master/examples/colab/tf_hub_generative_image_module.ipynb TF-Hub generative image model | The TensorFlow Hub Authors - Google] use of a [https://www.tensorflow.org/hub TF-Hub] module based on a generative adversarial network (GAN). The module maps from N-dimensional vectors, called latent space, to RGB images. |
| − | ** 3D Objects: [ | + | ** 3D Objects: [https://colab.research.google.com/github/tensorflow/lucid/blob/master/notebooks/differentiable-parameterizations/style_transfer_3d.ipynb 3D Style Transfer | Google] uses Lucid to implement style transfer from a textured 3D model and a style image onto a new texture for the 3D model by using a [https://distill.pub/2018/differentiable-parameterizations/#section-style-transfer-3d Differentiable Image Parameterization]. |
| Line 35: | Line 35: | ||
| − | <i>[ | + | <i>[https://developers.google.com/machine-learning/gan/generative Background: What is a Generative Model? | Google]</i> |
More formally, given a set of data instances X and a set of labels Y: | More formally, given a set of data instances X and a set of labels Y: | ||
Revision as of 17:33, 16 February 2023
YouTube search... ...Google search
- AI Solver
- Generative Query Network (GQN)
- Discriminative vs. Generative
- Natural Language Generation (NLG)
- Emergence from Analogies
- Generative Model | Wikipedia
- Synthetic Labeling
- Stable Diffusion | Stable Diffusion ... a latent text-to-image diffusion model capable of generating photo-realistic images given any text input
- Demos, generating...
- Music: Generating Piano Music with Transformer | I. Simon, A. Huang, J. Engel, C. "Fjord" Hawthorne - Google on Colab play with pretrained Transformer models for piano music generation, based on the Music Transformer model
- Faces: TF-Hub generative image model | The TensorFlow Hub Authors - Google use of a TF-Hub module based on a generative adversarial network (GAN). The module maps from N-dimensional vectors, called latent space, to RGB images.
- 3D Objects: 3D Style Transfer | Google uses Lucid to implement style transfer from a textured 3D model and a style image onto a new texture for the 3D model by using a Differentiable Image Parameterization.
- Three main types:
- Autoencoder (AE) / Encoder-Decoder
- Sequence Models
- Adversarial Networks
Background: What is a Generative Model? | Google
More formally, given a set of data instances X and a set of labels Y:
- Generative models capture the joint probability p(X, Y), or just p(X) if there are no labels.
- Discriminative models capture the conditional probability p(Y | X).
A generative model includes the distribution of the data itself, and tells you how likely a given example is. For example, models that predict the next word in a sequence are typically generative models (usually much simpler than GANs) because they can assign a probability to a sequence of words.
Informally:
- Generative models can generate new data instances.
- Discriminative models discriminate between different kinds of data instances.
Deep Generative Modeling
Agents
Generative Modeling Language
