Administrative Information
| Title | Model Fitting and Optimization |
| Duration | 150-180 min |
| Module | A |
| Lesson Type | Practical |
| Focus | Technical - Foundations of AI |
| Topic | Fitting and Optimization |
Keywords
model fitting,optimization,binary classification,regression,
Learning Goals
- Visualise and scale the features and labels to simply the classification problem.
- Use the metrics to evaluate the classification model.
- Tune the hyperparameters to improve the model performance.
Expected Preparation
Learning Events to be Completed Before
Obligatory for Students
- Students should have hands-on experience in python programming
- Students should have good understanding of Data exploration techniques
- Students should have reviewed lectures and demonstration on topics of Model Types, Model Evaluation, Model Fitting and Model Optimization
Optional for Students
None.
References and background for students
None.
Recommended for Teachers
- Machine Learning Basics Lecture 6: Overfitting (princeton.edu)
- Regularization - Colaboratory (google.com)
- Underfit-Overfit - Colaboratory (google.com)
Lesson materials
Instructions for Teachers
Follow the steps in the Colab.
Outline of lecture
| Duration (min) | Description | Activity | Material |
|---|---|---|---|
| 0-15 min | A brief overview of the tasks and learning goals | Instructions by the lecturer | colab practical link for lecturer |
| 15 - 40 min | Task 1 - Explore the dataset - Visualise and summarise the findings. Normalize and label the target variable. | Reporting - investigation of data (bias, redundancy, ethical) | |
| 40 - 75 min | Task 2 - Model Evaluation - Model Evaluation based on Train and Test data. | Coding | |
| 75 - 105 min | Task 3 - Model Optimization - Use hyperparameter tuning and modify the threshold to improve the performance. | Coding | |
| 105 - 135 min | Task 4 - Model Optimization - Summarise the model performance of Task 3 | Reporting - Summary | |
| 135-150 min | Summary of the practical | Conclusion by the lecturer |
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.