Course overview
The aim of this course is to develop skills in applying supervised, unsupervised and deep machine learning techniques to real-world data analytics problems. Linear regression, regularization, logistic regression, neural network architectures, neural network learning, convolutional neural network, recurrent neural network, long short-term memory, machine learning in practise, clustering, dimensionality reduction, anomaly detection, large-scale machine learning.
Course learning outcomes
- Design and implement supervised, unsupervised, and deep machine learning techniques in a range of real-world applications.
- Analyse different types of data and apply appropriate supervised, unsupervised, and deep machine learning techniques.
- Evaluate and adapt supervised, unsupervised, and deep machine learning techniques for real-world problem solving.
- Compare the fundamental issues and challenges of different supervised, unsupervised and deep machine learning techniques.
Degree list
The following degrees include this course