The course covers the foundations and modern methods of deep learning. Topics include multilayer neural networks, computational graphs and backpropagation, methods for stable training and generalization, convolutional networks and ResNet, representation learning, and self-supervised learning. RNN and LSTM models are studied as an introduction to attention mechanisms and Transformer architectures. The course also covers pretraining, fine-tuning, parameter-efficient adaptation methods such as LoRA, and modern generative models, including VAEs, autoregressive models, and diffusion models. Multimodal models are surveyed, and the course includes hands-on experience with PyTorch.
The course presents the main principles and methods of machine learning and their practical application. Topics include the end-to-end machine learning workflow, data preparation and leakage prevention, regression and classification, model evaluation and selection, regularization, decision trees and ensemble methods, KNN and SVM, clustering and dimensionality reduction. The course also introduces neural networks and deep learning, selected modern applications, foundation models and generative AI, as well as fairness, explainability, reproducibility, deployment, and model monitoring. Tutorials complement the theoretical material through demonstrations and practical work in Python.
As part of the course, the student will be exposed to all the development stages of an application or software package including: application design and development, interface design, algorithm implementation, architecture selection and database integration, methodology implementation, critical thinking, end-to-end development and testing, documentation and presentation, teamwork and project management.
This is a continuation course in which the student will be exposed to all the development stages of an application or software package, including: application design and development, interface design, algorithm implementation, architecture selection and database integration, methodology implementation, critical thinking, end-to-end development and testing, documentation and presentation, teamwork and management projects.
The course provides a comprehensive foundation in the fundamentals of artificial intelligence. The first part focuses on Search and Planning concepts. The second part focuses on methods of Probabilistic Reasoning. The theoretical material is accompanied by examples.
