Difference between revisions of "Generative AI"

From
Jump to: navigation, search
m
m
Line 29: 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 08:47, 8 March 2023

YouTube search... ...Google search


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