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

Attention is all you need

References and background for students

Recommended for Teachers

None.

Lesson materials

Lecture Slides

The materials of this learning event are available under CC BY-NC-SA 4.0.

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

More information

Click here for an overview of all lesson plans of the master human centred AI

Please visit the home page of the consortium HCAIM

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.

The materials of this learning event are available under CC BY-NC-SA 4.0

The HCAIM consortium consists of three excellence centres, three SMEs and four Universities