The course provides a practical introduction into  artificial intelligence methods with a focus on machine learning and it’s applications in computer science.Please consider also visiting: VK "Machine Learning and Deep Learning" (650.025) for an in-depth overview of neural networks and their applications.PR "Machine Learning and Deep Learning" (623.625) providing hands-on sessions with a focus on programming  of applications using deep neural networks "Selected Topics in Artificial Intelligence" (626.017) for an in-depth review of reinforcement learning methods. ”Current Topics in Multimedia Systems: Content Search with Deep Learning” (623.915) which among other interesting topics considers various architectures and applications of Deep Neural Networks to image/video processing and recognition.

Lectures with a student's project applying machine learning to a practical problem.

Introduction to AI and machine learningSupervised learning: classification and regressionUnsupervised learning: transformation of data and clusteringValidation of modelsOverview of the reinforcement learning

The course has makes no assumptions about the prior knowledge, but basic knowledge of the probability theory as well as of Python is a plus.

No prerequisites

Beginners:James, G., Witten, D., & Hastie, T. (2014). An Introduction to Statistical Learning: With Applications in R. SpringerRaschka, S. (2015). Python machine learning. Packt Publishing Ltd.Classics:Mitchell, T. (1997) Machine Learning. McGraw Hill.Bishop, C. M. (2006). Pattern Recognition and Machine Learning. Springer.Friedman, J., Hastie, T., & Tibshirani, R. (2009). The elements of statistical learning.  2nd edition, Springer.

Design and implementation of a project applying machine learning to solve a selected problem 

Students should demonstrate their ability to apply machine learning methods discussed in the course.

Grades are given based on a project proposal, a mid-term review presentation, and a final report.