Machine learning for biomedical applications

Course Aim:
This course aims to provide students with biomedical background an introduction to machine learning with biomedical data. The course covers some of the main models and algorithms for biomedical data clustering, classification and regression. Topics will include handling uncertain medical data using linear and logistic regression, regularization, probabilistic (Bayesian) inference, Support Vector Machines (SVMs), clustering, and dimensionality reduction, and support of those methods for several biomedical applications.
Course Contents:
Introduction -– Types of biomedical data (characteristics, properties, and specifications), Linear Regression - Instance-based Learning and Decision Tree Induction - Probabilistic (Bayesian) Inference (Linear regression, Logistic regression) - Artificial Neural Networks: perceptron - Ensemble learning - Clustering algorithms, k-means for different medical analysis data (signal, textual, and images), Hierarchical Clustering - Dimensionality reduction techniques, SVD/PCA, Biomedical applications of the prementioned methodologies.