Generative AI

At a high level, generative models encode a simplified representation of their training data, and then draw from that representation to create new work that’s similar, but not identical, to the original data.

Generative models have been used for years in statistics to analyze numerical data. But over the last decade, they evolved to analyze and generate more complex data types. This evolution coincided with the emergence of three sophisticated deep learning model types:

• Variational autoencoders or VAEs, which were introduced in 2013, and enabled models that could generate multiple variations of content in response to a prompt or instruction.
  
  
• Diffusion models, first seen in 2014, which add "noise" to images until they are unrecognizable, and then remove the noise to generate original images in response to prompts.
  
  
• Transformers (also called transformer models), which are trained on sequenced data to generate extended sequences of content (such as words in sentences, shapes in an image, frames of a video or commands in software code). Transformers are at the core of most of today’s headline-making generative AI tools, including ChatGPT and GPT-4, Copilot, BERT, Bard and Midjourney.