Generative Model

Deep Generative Model (DGM), Gen AI, Generative AI

We define a generative model as fully specifying. For non-generative

Discriminative Model model, we are only interested in a conditional mapping

Classical supervised & unsupervised learning predict | classify | cluster with resulting number, discrete, class or probability. The result is Natural language | Image | Audio

Generative Model Notion

Generative AI Property

Text to Task Model

RAG

Retrieval-Augmented Learning

Fact Learning

Tool learning

AI Memory

https://www.researchgate.net/figure/Overview-of-deep-generative-models_fig1_380573076

Lesson

generative-ai

GoogleCloudPlatform • Updated 2024 Oct 28 11:45

GenerativeAIExamples

NVIDIA • Updated 2024 Oct 28 10:51

Generative AI for Beginners

Description

https://microsoft.github.io/generative-ai-for-beginners/#/

Generative AI: autocomplete for everything

This blog post is co-authored by Noah and roon. roon is a researcher at a prominent AI company, and he also posts humorously on Twitter. Because this is a joint post, we sometimes refer to one of us in the third person.

https://noahpinion.substack.com/p/generative-ai-autocomplete-for-everything

Generative AI: A Creative New World

Applications Here are some of the applications we are excited about. There are far more than we have captured on this page, and we are enthralled by the creative applications that founders and developers are dreaming up.

https://www.sequoiacap.com/article/generative-ai-a-creative-new-world/

Model and learn likelihood from data distribution

Estimate prior and deduce posterior

데이터의 분포를 학습하여 생성 규칙을 파악

can compute how probable any given model instance is

Can be learned using images from just a single category

Generative Learning Notion

Discriminant Analysis

Naïve Bayes

Generative Model

Deep Generative Model (DGM), Gen AI, Generative AI

Lesson

Model and learn likelihood from data distribution

Recommendations