Generative AI

This course provides an immersive and comprehensive journey into the core technologies that are shaping the future of artificial intelligence. We begin by meticulously exploring the attention mechanism, a revolutionary concept that allows models to weigh the importance of different parts of an input sequence. This foundational understanding will then lead us to transformers and sequence-to-sequence models, where you'll see how attention mechanisms are leveraged to handle complex tasks like machine translation and text summarization with unprecedented accuracy. By the time we conclude this section, you'll have a deep theoretical grasp of how these architectures function and why they have become the industry standard.The curriculum is not just theoretical; it's intensely practical. You'll gain hands-on experience by working on Python Code using JSON file, a standard for data exchange, and learn to implement Retrieval-Augmented Generation (RAG), a powerful technique that enhances language models with external knowledge. The course culminates in an example where all these skills applied to construct a simple AI agent in Python. This coding based approach ensures you don't just understand the concepts but can also code basic AI systems. By the end of this course, you will have a solid foundation in the basics of both the theory and practice of  AI and intelligent agents.Section 1, "Introduction," covers the attention mechanism in transformers and how different components fit together. Section 2, "Sequence to Sequence Models," focuses on understanding and using Seq2seq models with attention. The third section, "Coding in Python," includes topics such as coding transformer basics, diving deeper into the attention mechanism with code, and the transformative power of attention in AI models. The final section, "Advanced Topics," explores AI agents, agentic AI, and practical applications like understan