SC4000 - Machine Learning
Course Summary
This course provides an introduction to a wide range of fundamental machine learning algorithms. It focuses primarily on core concepts and algorithms, which is very helpful for further studies in machine learning. The topics covered include:
- Machine learning, its types, and applications
- Bayesian classifiers (e.g., naive Bayes, Bayesian belief networks)
- Decision trees
- Artificial neural networks
- Support vector machines
- Regression models
- k-nearest neighbour classifiers
- Ensemble learning
- Clustering (e.g., k-means, hierarchical)
- Density estimation
- Dimensionality reduction
Workload
The assessment consists of a group project and a final exam. The group project can be quite demanding since each member needs to continuously train models to improve their score in the Kaggle competition. The final exam is fairly manageable as long as you practice past exam papers.
Projects
The group project involves participating in a Kaggle competition (you can choose from a selection of competitions) or completing a research project. The project may cover topics beyond what is taught in the course, so expect to do some self-learning.
Tips to Do Well
Start the project early and make sure to attend all the lectures.
Written by U