📚 Syllabus & Course Curriculum
Data Science & Analytics
Module-by-module breakdown of Large Language Models (LLMs) and Generative AI, from foundations to a certified capstone project.
Mechanism
• Tokenisation, embeddings and self-attention explained without the mathematics
• Pretraining, instruction tuning and preference optimisation as three stages
• Context windows, and why a model forgets material inside its own window
Prompting
• Instruction structure, few-shot examples and output format constraints
• Chain-of-thought and its uneven benefit across task types
• Systematic evaluation instead of judging a prompt from three examples
Retrieval
• Chunking, embeddings and vector stores in a RAG pipeline
• Retrieval quality as the usual bottleneck, not the generation step
• Hybrid search, reranking and citation so an answer can be checked
Adaptation
• LoRA and parameter-efficient methods against full fine-tuning
• When fine-tuning helps format and tone but cannot add knowledge
• Dataset construction and the cost of getting training examples wrong
Production
• Evaluation sets, regression testing and LLM-as-judge with its biases
• Latency, cost per request and caching as design constraints
• Hallucination, prompt injection and guardrails at the application boundary
Earn government-registered certification in Large Language Models (LLMs) and Generative AI
e-Certificate and e-Marksheet issued on successful completion.
