ISEA2013 Foundations of AI and Machine Learning (5 op)

This course provides a foundational understanding of artificial intelligence and machine learning. It introduces the key differences between supervised and unsupervised learning, as well as the basic characteristics of linear and non-linear models. The course also covers essential mathematical concepts, optimization methods, and computational considerations, along with the role of hyperparameters in controlling the learning process, model structure, and overall performance. Students gain practical skills in implementing machine learning methods, evaluating model performance, and improving results through model optimization.

In addition, the course offers an introduction to neural networks and the basic principles of deep learning, familiarizing students with common architectures such as feedforward networks, convolutional neural networks (CNNs), and recurrent neural networks (RNNs), and their typical application areas. 

Upon successful completion of the course, students will be able to:

• Explain the core concepts of artificial intelligence and machine learning

• Distinguish between supervised and unsupervised learning approaches

• Describe the characteristics and differences of linear and non-linear models

• Apply basic mathematical and optimization concepts relevant to machine learning

• Implement simple machine learning models using appropriate tools and methods

• Evaluate model performance using suitable metrics and validation techniques

• Explain the role of hyperparameters and apply basic techniques for their tuning

• Describe the fundamental principles of neural networks and deep learning

• Identify common neural network architectures (e.g., feedforward, CNN, RNN) and their typical applications

• Collaborate in a group to implement elementary AI and machine learning algorithms and present the results. 

Programming skills and basic knowledge in vectors and matrices, derivatives and gradients, probability and basic statistics.