|SCIENTIFIC DISCIPLINARY SECTOR||INF/01|
This course aims at providing the basics of Artificial Intelligence for biomedical applications. Students will learn machine and deep learning methods and how to set up an experimental pipeline that guarantees reproducible results. All classes are divided into theory and practice.
Il corso introdurrà i concetti ei principi fondamentali dell'apprendimento automatico e dell'intelligenza artificiale applicata alla medicina
Recommended background knowledge
Probability and basic statistics
Duration of teaching 48 hours (1/2 theory 1/2 practice).
Introduction to Artificial Intelligence. Examples of AI in medicine and biology. Data driven methods: supervised /unsupervised. Supervised: classification/regression.Unsupervised: clustering and visualization. Bias and Generalization
Machine learning methods for prediction. Data: issues and challenges. Methods: examples of predictive models for diagnosis or prognosis. Detection of disease. Disease progression prediction. Disease staging. Regularization methods. Measures to assess the classification model
Deep learning methods for prediction. Examples of predictive methods for diagnosis or prognosis. Early detection of disease. Disease progression prediction. Disease staging. Deep learning. Multilayer perceptron. Model dependency on learnable parameter and model stochasticity
Applications of AI in medicine. Medical image prediction. Deep learning (CNN). Graph neural networks
Examples of variable selection in medicine. Case study: identification of pathogenic molecular variables. SVM-RFE. Lasso and sparsity inducing methods.Variable selection for genomics
Office hours: Appointment by email
Classes will start on the last week of September 2022. The schedule of all courses can be found on EasyAcademy.
All class schedules are posted on the EasyAcademy portal.