Objectives and outcomes
Introducing basic concepts of machine learning and solving problems using machine learning techniques. Understanding matrix problems, defining criterion functions using probabilities and solving regression and classification problems.
Lectures
Introduction. A brief overview of probability theory for machine learning purposes. Evaluation of machine learning systems. Linear regression. Estimation techniques. Regularisation techniques. Bayesian learning. Dimensionality reduction. Optimisation. Logistic regression. Modular backpropagantion. Neural networks. Support Vector Machines (SVM). Decision trees, ensemble algorithms, Random Decision Forest (RDF). Introduction to deep learning.
Practical classes
Implementation of machine learning algorithms covered in lectures. TensorFlow. Logistic regression. Linear
regression. Instance-based methods. Language processing, Naive Bayes. Neural Networks. OpenCV. Clustering. Dimensionality reduction. SVM.