Artificial Intelligence and Automatic Learning in Biomedical Systems

Course Holder: Prof. dr. eng. Bogdan IONESCU
Laboratory holder: Prof. dr. eng. Bogdan IONESCU

The course aims to familiarize students with the concept of machine learning applied to biomedical problems. General introduction to the concept and existing paradigms, concrete medical applications and available software utilities. Explanation of processing and representation techniques for input data, related content descriptors, data normalization and decorrelation. Classical supervised classification techniques, such as Support Vector Machines or Random Forests, are introduced. Perspectives on neural network classification techniques are also presented, from simple architectures such as Multi-Layer Perceptrons to deep Convolutional Neural Networks architectures. Finally, the problem of evaluating the performance of learning systems is addressed. Classification systems are exemplified in specific applications ranging from the detection and monitoring of neurodegenerative disorders such as Parkinson's or Alzheimer's, to the analysis of epileptic seizures and sleep disorders.)