In this lecture, we will learn some basic methods in machine learning, their mathematical derivations, and their implementation on computers.
Learn about neural networks and clustering, which are the basic methods of machine learning, and acquire the mathematical basics for deriving them so that they can be implemented and operated on a computer.
Machine Learning, Artificial Intelligence, Deep Learning, Pattern Recognition
✔ Specialist skills | Intercultural skills | Communication skills | Critical thinking skills | ✔ Practical and/or problem-solving skills |
Classes mainly consist of lectures and exercises.
Course schedule | Required learning | |
---|---|---|
Class 1 | Introduction | Basics of mathematics required for machine learning |
Class 2 | Linear models (Regression) | Linear regression model and its learning method |
Class 3 | Linear Models (Classification) | Logistic regression, support vector machine |
Class 4 | Neural Network (Basic) | Perceptron, activation function, back propagation method |
Class 5 | Neural Network (Advanced) | Convolutional neural network (CNN), recurrent neural network (RNN) |
Class 6 | Clustering | k-means, Gaussian mixture model (GMM) |
Class 7 | Matrix Decomposition | Principal component analysis (PCA), independent component analysis (ICA), non-negative matrix factorization (NMF) |
To enhance effective learning, students are encouraged to spend approximately 100 minutes preparing for class and another 100 minutes reviewing class content afterwards (including assignments) for each class.
They should do so by referring to textbooks and other course material.
No textbook used
Reference Book: Pattern Recognition and Machine Learning, C. M. Bishop, Springer
Students will be assessed on their understanding of the basic theory of machine learning and its application. Exercise problems 70%, final examination 30%.
It is desirable to have a basic knowledge of linear algebra and calculus.