This course provides a comprehensive introduction to deep neural networks. Major topics include multilayer perceptrons, convolutional neural networks, practical aspects of model creation from scratch and training, sequence modeling with recurrent neural networks and transformers, and generative probabilistic modeling. Advanced topics, including Bayesian deep learning, will also be explored. Students will learn basic concepts of deep learning and hands-on experience to solve real-word problems. This course requires a strong background in linear algebra, probability and statistics, and machine learning. Python will be used for all the assignments. Proficiency in Python or being able to quickly learn it is required.

This course will cover core topics in data mining and their applications. The topics covered include classification, association, clustering, and anomaly detection. The course aims at helping the students understand different techniques that can be applied for different problems and their limitations, evaluate the results and select the appropriate methods when faced with a new problem. It will give students hands-on experience applying those techniques by implementing a complete solution using one or more data mining software packages.