Administrative Information
Title | Generative Models, Transform Deep Learning and Hybrid learning Models |
Duration | 45 - 60 |
Module | C |
Lesson Type | Lecture |
Focus | Technical - Future AI |
Topic | Advances in ML models through a HC lens - A result Oriented Study |
Keywords
Generative Models,Attention Detection,Query-Key-Value,Transform models,Hybrid Models,
Learning Goals
- Understand the class of Generative Models and explore its key features.
- Explain the concept and design of Transformer Architectures
- Elaborate the configuration of Hybrid Models
Expected Preparation
Learning Events to be Completed Before
Obligatory for Students
- Introduction to machine learning and deep learning concepts given in previous lectures
Optional for Students
References and background for students
Recommended for Teachers
None.
Lesson materials
Instructions for Teachers
In this lecture, our primary objectives are threefold. Firstly, we aim to comprehensively understanding of Generative Models, focusing on their underlying mechanisms and core features. Secondly, we will discuss the significance of Transformer Architectures, particularly in the context of Natural Language Processing (NLP). Lastly, the lecture will elaborate on the various configuration of Hybrid Models, emphasizing the fusion of diverse elements to enhance machine learning performance.
Outline
Duration | Description | Concepts |
---|---|---|
15 min | Introduction to Generative Models, Classification of Generative Models | What are generative models?, Why are they important? What can they be used for? Classification, Key features, Examples |
20 min | Introduction to the Transformer architectures | Transformer architecture, state-of-the-art transformers such as BERT and GTP |
10 min | Introduction to Hybrid learning | What is hybrid learning?, Why is it important?, What can they be used for? |
5 min | Conclusion, questions and answers | Summary |
Acknowledgements
The Human-Centered AI Masters programme was Co-Financed by the Connecting Europe Facility of the European Union Under Grant №CEF-TC-2020-1 Digital Skills 2020-EU-IA-0068.