Administrative information


Title Regularization Techniques
Duration 60 min
Module B
Lesson Type Lecture
Focus Technical - Deep Learning
Topic

Regularization Techniques

 

Keywords


Regularization, Callbacks, Gridsearch,

 

Learning Goals


 

Expected Preparation


Learning Events to be Completed Before

None.

Obligatory for Students

None.

Optional for Students

None.

References and background for students:

  • John D Kelleher and Brain McNamee. (2018), Fundamentals of Machine Learning for Predictive Data Analytics, MIT Press.
  • Michael Nielsen. (2015), Neural Networks and Deep Learning, 1. Determination press, San Francisco CA USA.
  • Charu C. Aggarwal. (2018), Neural Networks and Deep Learning, 1. Springer
  • Antonio Gulli,Sujit Pal. Deep Learning with Keras, Packt, [ISBN: 9781787128422].

Recommended for Teachers

None.

 

Lesson Materials


 

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

 

Instructions for Teachers


This lecture will introduce students to the fundamentals of the hyperparameter tuning. We will use the Census Dataset as the examples of the use and outcomes from the regularisation techniques. The Adult Census dataset is a binary classification problem. The goal of this lecture is to introduce several forms of regularisation, starting with weight initialisers, bias, co-adaption, callbacks, a grid search for automatic hyperparameter tunning, and additional regularisation checking techniques. The goal is to identify techniques to support the development of generalisable models with limited co-adaption to learn the function and not the data. Some of these techniques also improve training time, thus can reduce the computation needed for larger models.

Outline

Time schedule
Duration (Min) Description
10 Weight initialisers and bias
10 Co-adaption
10 Callbacks
20 GridSearch
10 Additional checks

 

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

HCAIM Consortium