Difference between revisions of "Generative AI"
m |
m |
||
| Line 8: | Line 8: | ||
[https://www.google.com/search?q=Generative+Modeling ...Google search] | [https://www.google.com/search?q=Generative+Modeling ...Google search] | ||
| + | * [[Assistants]] ... [[Hybrid Assistants]] ... [[Agents]] ... [[Negotiation]] | ||
| + | * Conversation [[Generative AI]] tools: | ||
| + | ** [[ChatGPT]] | [[OpenAI]] | ||
| + | ** [[Bard]] | [[Google]] | ||
| + | ** [[Perplexity]] | Perplexity.ai ... current information, including footnotes with links to the sources of the data | ||
| + | ** [[You]] | You.com ... the AI search engine you control; YouChat, YouCode, YouWrite, YouImagine, YouStudy, & YouSocial | ||
| + | ** [[Neeva]] | ||
* [[AI Solver]] | * [[AI Solver]] | ||
* [[Generative Query Network (GQN)]] | * [[Generative Query Network (GQN)]] | ||
| Line 22: | Line 29: | ||
** 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. | ** 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: [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]. | ** 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]. | ||
| − | + | ||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
* Three main types: | * Three main types: | ||
** [[Autoencoder (AE) / Encoder-Decoder]] | ** [[Autoencoder (AE) / Encoder-Decoder]] | ||
Revision as of 08:44, 8 March 2023
YouTube search... ...Google search
- Assistants ... Hybrid Assistants ... Agents ... Negotiation
- Conversation Generative AI tools:
- AI Solver
- Generative Query Network (GQN)
- Discriminative vs. Generative
- Natural Language Generation (NLG)
- Emergence from Analogies
- Generative Model | Wikipedia
- Synthetic Labeling
- Video Synthesis
- Generated Image
- Generative AI for Business Analysis
- 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.
Roblox
Roblox is a gaming platform and publishing system that allows users to create and play 3D games online. Some of the technologies used with Roblox are:
- Roblox Studio, a development environment that provides tools for creating and publishing games on Roblox
- Roblox VR, a virtual reality feature that enables users to enjoy the games in immersive 3D environments
- Generative AI, a new technology that uses artificial intelligence to generate code, assets, and content for Roblox games
- Amazon AWS, a cloud computing service that hosts Roblox’s servers and data centers
Deep Generative Modeling
Agents
Generative Modeling Language
