Course material & Lecture notes
Artificial Intelligence (UCU; Fall 2025, 2024)
This course provides a structured introduction to the foundations of Artificial Intelligence, combining classical algorithmic approaches with modern machine learning methods. The emphasis is on understanding core principles, modeling assumptions, and practical implications across learning, optimization, and perception tasks as well as practical applications.
Course materials (Fall 2025)
2025-15-09
PDF
[L02] Machine Learning: Supervised Learning
Introduction to supervised learning, including problem formulation, datasets and
labels, loss functions, and empirical risk minimization. Examples such as linear
regression, with discussion of bias-variance tradeoff, overfitting, and ensemble
methods (bagging and boosting).
2025-22-09
PDF
[L03] Machine Learning: Supervised Regularization
Regularization in supervised learning, focusing on bias-variance tradeoff,
overfitting and generalization. L1 and L2 regularization, ridge and lasso
regression, and their effect on model complexity and stability.
2025-29-09
PDF
[L04] Machine Learning: Unsupervised Dimensionality Reduction
Unsupervised learning and dimensionality reduction. PCA and eigenvalue
interpretation, clustering methods such as k-means, and the curse of
dimensionality. Overview of nonlinear techniques including t-SNE and UMAP.
2025-27-10
PDF
[L07] Computer Vision: Introduction
Introduction to computer vision, covering image representation, color spaces,
basic image processing, and classical vision tasks. Overview of modern
deep learning-based vision pipelines, models, and training approaches.
Course materials (Fall 2024)
2024-23-09
PDF
[L04] Machine Learning: Supervised Learning
Introduction to supervised learning, including problem formulation, datasets and
labels, loss functions, and empirical risk minimization. Examples such as linear
regression, with discussion of bias-variance tradeoff, overfitting, and ensemble
methods (bagging and boosting).
2024-30-09
PDF
[L05] Machine Learning: Supervised Regularization
Regularization in supervised learning, focusing on bias-variance tradeoff,
overfitting and generalization. L1 and L2 regularization, ridge and lasso
regression, and their effect on model complexity and stability.
2024-04-11
PDF
[L10] Machine Learning: Unsupervised Dimensionality Reduction
Unsupervised learning and dimensionality reduction. PCA and eigenvalue
interpretation, clustering methods such as k-means, and the curse of
dimensionality. Overview of nonlinear techniques including t-SNE and UMAP.
