Generative AI: From Theory to Product Launch

Generative AI (GenAI) is an exciting new frontier of technology that opens up seemingly endless creative possibilities. This course provides a glimpse of generative models’ capability by showcasing some of their most impressive applications. It will empower you to leverage GenAI and large language models (LLMs) like DALL·E and GPT-2.

You’ll learn about the evolution of machine translation systems, from the early 1950s to the current state-of-the-art generative models. You’ll learn about the building blocks of Transformer networks, including CNNs, RNNs, etc. This will be supplemented by an overview of the components of a GenAI system. Next, you’ll learn about transformer models and their variations: Vision Transformers (ViT) and multimodal transformers.

You’ll explore the state-of-the-art models for text, image, and video generation models through the practical exercises. You’ll dive deep into the impact of GenAI across fields and industries, fueling the development and launch of GenAI-based products.

1. Familiarity with generative AI and its evolution over the years
2. Understanding of core components such as CNNs, RNNs, autoencoders, and GANs
3. Familiarity with real-world applications of generative AI empowered by the transformers and generative AI systems
4. Familiarity with popular text and image generation models such as DistilBERT, GPT-2, GPT-3, GPT, DALL·E, Stable Diffusion, and Gen-2
5. Practical experience with state-of-the-art multimodal models used to generate text, images, and videos