Generative AI: Learn about the next AI frontier

Embark on a transformative journey into the world of Generative AI, a rapidly evolving field reshaping how we interact with technology. This course explores the exciting possibilities and potential challenges of Generative AI, a technology increasingly integral to our daily lives.

You'll delve into the theoretical foundations of Generative Models, covering diverse modalities including:

• Text-to-Text (Txt2Txt): Understanding how AI generates text.
• Image-to-Text (Img2Txt): Exploring AI's ability to describe images.
• Text-to-Image (Txt2Img): Discovering AI's power to create images from text prompts.
• Image-to-Image (Img2Img): Learning how AI transforms images based on input.
• Text-to-Voice (Txt2Voice): Investigating AI-powered voice synthesis.
• Voice-to-Text (Voice2Text): Exploring speech recognition technologies.

We'll examine the State-of-the-Art (SoTA) models driving innovation in each area. This includes a deep dive into Transformers, the core architecture behind many modern AI systems, and Large Language Models (LLMs). Learn about Generative Pre-trained Transformers (GPT), the technology powering ChatGPT for advanced text generation.

Explore the fascinating world of Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and Diffusion Models like DALL-E and Stable Diffusion for groundbreaking image generation. We'll also investigate VALL-E and its capabilities in voice generation.

This course isn't just theoretical! Gain practical experience by:

• Building simple Language Models from scratch.
• Creating a ChatGPT clone using OpenAI APIs, exploring real-world OpenAI use cases with GPT-3.5 and ChatGPT, and DALL-E.
• Utilizing Hugging Face Transformers for advanced natural language processing.
• Mastering Stable Diffusion for high-quality image creation.

Join us and unlock the potential of Generative AI!