Programme outline
Learning objectives and structure
By the end of the course, participants will:
- Understand key concepts in Natural Language Processing (NLP) and Generative Artificial Intelligence, including tokenisation, embeddings, and large language models (LLMs).
- Build and deploy simple Artificial Intelligence (AI) models using tools
- Explore and apply low-code/no-code tools for designing conversational workflows and NLP pipelines.
- Learn the fundamentals of Retrieval-Augmented Generation (RAG) and integrate LLMs with external knowledge sources for enhanced AI applications.
- Develop and deploy a hands-on AI project, applying skills from the module to create and showcase a Generative AI solution.
Day 1
- Overview of Natural Language Processing (NLP)
- Key concepts: tokenisation, stemming, lemmatisation, embeddings
- Common NLP applications (e.g., sentiment analysis, translation, summarization)
- What is Generative AI? How large language models (LLMs) like GPT understand and generate text? Popular models and their use cases.
- Hands-on activities on tokenisation and using Word2Vec to visualize word embedding
- Hands-on activities on sentiment analysis, summarisation, object recognition and question-answering
- Hands-on activities on running LLMs and building GenAI apps
Day 2
- Exploring low-code/no-code tools for building AI applications
- Hands-on activities on designing conversational workflows and creating simple pipelines for NLP tasks
- Introduction to Retrieval-Augmented Generation (RAG)
- Hands-on activities on integrating LLMs with external data sources, testing and deploying the RAG app
- Hands-on activities on building AI-powered chatbots and assistants
Day 3
- Project consultation
- Project presentation
Assessment
- Assignment
- Project