|Module Name||Machine Learning|
|Module Short Title|
|Semester Taught||Michaelmas Term|
2 lecture hours per week, and a few additional lab sessions (around four in total).
|Module Personnel||Assistant Professor Joeran Beel & Professor Douglas Leith|
Students who complete this module should be able to:
- CS4LO1 Decide when machine learning is an appropriate method to solve a problem
- CS4LO2 Understand how machine learning works.
- CS4LO3 Apply machine-learning frameworks to solve real-world problems, and adjust and extend existing algorithms when necessary.
The principal aim of this module is to provide students with a working understanding of machine-learning techniques and their application to solve real-world problems.
- Machine Learning Basics (Application Areas, Challenges, Alternatives to Machine Learning)
- Machine Learning in Action (Datasets, Frameworks, Evaluation)
- Cross-validation and confidence intervals
- Overfitting/underfitting (bias-variance trade-off)
- Machine Learning Algorithms
- Linear Regression
- Logistic Regression
- Support Vector Machines
- Kernel Methods
- k-Means Clustering and Mixture Models for Unsupervised Learning
- Neural Networks
- Deep Learning Algorithms
- Use of gradient descent, and extensions for improved scalability (stochastic gradient descent etc)
- Probabilistic interpretations of ML algorithms. Maximum Likelihood and MAP estimators.
- Recommender systems
|Recommended Reading List|
A first course in probability and a basic knowledge of linear algebra
|Academic Year of Data|