This module prepares learners for machine learning interviews by covering ML roles and responsibilities, core concepts, key algorithms including regression, clustering, and ensemble methods, and practical applications such as tumour detection, movie recommendations, and ad classification.

This module establishes foundational knowledge of AI, ML, deep learning, and generative AI, tracing the history of these technologies, examining AI types from narrow to superintelligence, and exploring the relationship between Gen AI and ML.

This module covers the types of generative AI, how machines learn, types of machine learning, an introduction to data science, and foundational concepts of prompt engineering, foundation models, and transformers.

This module provides a comprehensive study of LLMs, covering their fundamentals, evolution, principles, axioms, pre-training and fine-tuning, types, significance, and applications along with their pros and cons.

This module surveys generative AI tools including productivity and writing tools, ChatGPT, image/video/music generation, and the open-source Llama model.

This module provides a broad view of generative AI's cross-industry applications, exploring its domains, capabilities, pros and cons, use cases, and future scope alongside associated tools.

This module provides an in-depth examination of LLM hallucinations, covering their types, root causes, measurement metrics, and strategies to reduce their occurrence.

This module addresses the key challenges and limitations of generative AI, supported by a real-world Google case study.

This module equips learners with practical strategies for deploying generative AI in business, covering implementation approaches, the Gen AI project lifecycle, and use case identification across industries.

This module provides hands-on instruction for building a chatbot using the OpenAI API.

This module covers working with open-source large language models via the Hugging Face platform.

This module covers the practical implementation of Retrieval-Augmented Generation (RAG) architecture by customising LLM models using LangChain and OpenAI.

This module introduces Amazon BedRock including its pricing structure, and provides hands-on experience with the Mistral 7B Instruct model.

This module explains key LLM model parameters — Top-P, Temperature, and Top-K — and how they influence model output behaviour.

This module introduces the foundational principles of prompt engineering for effective interaction with large language models.

This module covers zero-shot, single-shot, and few-shot prompting techniques and their implementation using LangChain.

This module provides hands-on implementation of Google Gemini generative models, covering setup, text reformatting, vision capabilities, chat history, token counting, and LangChain integration.

This module covers the prerequisites and practical steps for connecting LangChain with Amazon BedRock, including AWS CLI configuration for Python integration.

This module guides learners through the end-to-end development of a chatbot, covering prerequisites, backend and frontend development, and deployment using Streamlit.

This module covers the fundamentals of LLM fine-tuning with a practical demonstration of fine-tuning a BERT model for spam classification using Hugging Face.

This module introduces DeepSeek as an emerging generative AI tool, covering its key features, unique differentiators, a comparison with ChatGPT, and a forward-looking view of generative AI through DeepSeek's development roadmap.