The course discusses fundamentals and recent advances made in the field of computational
intelligence. The course focuses on highlighting the latest tools of machine learning and
approximate reasoning for building accurate models based either on collected data or past
experiential knowledge stored in the form of rules base. The course covers fundamental aspects
of machine learning for building model prediction and powerful classifiers. It highlights concepts
in supervised and unsupervised learning, artificial neural networks, deep learning, feature
extraction, feature selection, dimensionality reduction, classification and clustering, support vector
machines. It also tackles aspects related to approximate reasoning based on fuzzy set theory to
build reliable and easily interpreted inference engines when data is scarce. Various performance
metrics will be studied to assess the validity of the produced models. Throughout the course,
multiple examples and case studies are provided in significant application domains, from
autonomous driving to intelligent manufacturing, from natural language understanding to speech
recognition and computer vision, from stock market prediction to disease early detection and
diagnosis.