From the course: Python for Data Science and Machine Learning Essential Training Part 2

Unlock this course with a free trial

Join today to access over 25,300 courses taught by industry experts.

Deep dive into generative AI models

Deep dive into generative AI models

Quick note before we dive in. This is a high-level sampler chapter and not, of course, a full GenAI implementation module. Today, the most common GenAI systems you'll hear about in practice are large language models, diffusion models for image generation, and embeddings that power search and retrieval. In this video, we'll zoom out and map the broader landscape, including foundational model families like GANs and VAEs, so that you have the right mental model of what fits where. Now let's explore the diverse landscape of generative models, which are at the forefront of AI's ability to create new synthetic data that mimics real-world distributions. Generative models are primarily distinguished by their architecture and the statistical methods they employ to generate data. At the heart of this landscape are several key types of models. There's Generative Adversarial Networks or GANs, and these involve two neural networks, the…

Contents