Week 1 |
Machine Learning Paradigms
|
The chapter presents an in-depth exploration of machine learning and its various paradigms, including supervised, unsupervised, and reinforcement learning, providing foundational knowledge of the algorithms that animate them. Through this lens, students will gain a holistic view of the machine learning field and its applications, preparing them to comprehend and differentiate between the approaches and their usages. |
Week 2 |
Regression Analysis and Kernel Methods
|
Focusing on regression and kernel-based learning strategies, this chapter equips students with robust analytical tools to model and interpret complex data. By investigating data patterns and making predictive judgments, students will learn to apply these methods in solving real-world problems, thereby solidifying their understanding of these vital machine learning techniques. |
Week 3 |
Clustering Algorithms
|
This chapter dives into unsupervised learning through the study of clustering algorithms, uncovering the many ways machine learning finds patterns within unlabelled data. It emphasises the importance of these algorithms in identifying natural groupings in data, a critical skill for areas with vast, undocumented datasets. |
Week 4 |
Decision Trees and Random Forests
|
Addressing the powerful tools of decision trees and random forests, this chapter merges theoretical principles with practical applications, illustrating how these methodologies contribute to insightful data analysis and robust prediction models, and are fundamental to the machine learning toolkit. |
Week 5 |
Generative Learning Algorithms
|
Generative machine learning models, including Naive Bayes, GMM, and Generative Adversarial Networks, are the focal point of this chapter, which delves into the world of algorithmic content generation, providing insights into their capacity for modelling and synthesis, essential for understanding AI creativity. |
Week 6 |
Support Vector Machines (SVMs) and Kernel Trick
|
Support Vector Machines (SVMs) and the kernel trick take centre stage, introducing another dimension to machine learning classification problems. The power of SVMs in optimising decision boundaries and dealing with higher-dimensional data is unpacked, extending students' capabilities in binary classification. |
Week 7 |
Neural Networks
|
Here, students traverse the domain of neural networks and deep learning, from early perceptrons to state-of-the-art architectures, covering essential concepts such as network layers, activation functions, and backpropagation, setting the scene for understanding the profound impact of these models. |
Week 8 |
Algorithms and Optimising Models
|
A critical analysis of machine learning algorithms is essential, and this chapter provides the methodologies for evaluating and fine-tuning models to ensure that they generalise beyond their training data, which is an indispensable skill for any machine learning professional. |
Week 9 |
MLOps and Model Deployment
|
To convey the practicality of machine learning in industry, this chapter introduces MLOps, combining machine learning with operations to streamline and scale model deployment. It encapsulates best practices for sustainable machine learning workflows, optimisation, and maintenance. |
Week 10 |
Professional Development
|
Culminating the module, this chapter encourages students to reflect on their professional development within applied machine learning. It paves the way for constructing a learning strategy that aligns with their career objectives, fostering continuous advancement and innovation in their future endeavours. |