Machine Learning Modules

Learning Outcomes:

• Have a better understanding of the of role machine learning in future industry.
• Identify skill sets required to become proficient in machine learning.
• Know about the pitfalls of machine learning and ways to address it.

Collaborative Discussion 1:

Learning Outcomes:

• Undertake basic EDA.
• Understand the dataset.
• Prepare the dataset for machine learning.

Collaborative Discussion 1:

Learning Outcomes:

• Gain theoretical understanding of correlation and regression.
• Understand how to compute correlation and regression.
• Be able to apply these statistical techniques in real world scenario.

Collaborative Discussion 1:

e-Portfolio Activity:

Learning Outcomes:

• Undertake regression modelling with complex dataset.
• Evaluate the results to optimise the model.
• Know about more about the scikit-learn library of Python.

Team Project colleagues:

Learning Outcomes:

• Understand the logic which underpins clustering.
• Identify skill sets required to evaluate the results of cluster analysis.
• Understand the pitfalls of clustering techniques.

e-Portfolio Activity:

Learning Outcomes:

• Undertake clustering analysis on large datasets.
• Use right Python libraries for clustering.
• Evaluate and interpret the results.

Development Team Project:

Learning Outcomes:

• Gain a critical and detailed understanding of the ANN.
• Design and develop simple ANN artefacts.
• Critique and contextualise emerging research in ANN.

e-Portfolio Activity:

Learning Outcomes:

• Understand the error handling mechanism of ANN.
• Design and develop more ANN artefacts.
• Critique and contextualise emerging research in the area of ANN.

Collaborative Discussion 2:

e-Portfolio Activity:

Learning Outcomes:

• Understand the application and importance of computer vision
• Undertake basic computer vision related tasks.

Collaborative Discussion 2:

e-Portfolio Activity:

Learning Outcomes:

• Understand the core advancements in NLP and how they are transforming industries.
• Apply modern NLP models using Transformer architectures.
• Evaluate NLP models using domain-specific metrics.
• Critically assess and improve NLP models using hyperparameter tuning and transfer learning.

Collaborative Discussion 2:

Learning Outcomes:

• Understand the importance of model selection, evaluation, and optimisation.
• Undertake hyperparameter tuning to enhance model performance.
• Apply appropriate evaluation metrics for different ML tasks.
• Explore MLOps principles for continuous model improvement and monitoring.

e-Portfolio Activity:

Individual Presentation:

Learning Outcomes:

• Understand the challenges and opportunities of industry 4.0 revolution.
• Appreciate the impact of machine learning in future societies.

End of Module Assignment: