Course detail

Artificial Intelligence and Machine Learning

FIT-SUIAcad. year: 2024/2025

Overview of methods for solving AI tasks, including game playing. Logic and its use in task solving and planning. PROLOG vs. AI. Basic tasks of machine learning, metrics for quality assessment. Basic approaches to ML - decision trees, version spaces, reinforcement learning, active learning. Probabilistic approach to classification and recognition, Gaussian model, its interpretation and training. Linear and logistic regression. Support vector machines. Neural networks (NN) - basic building blocks, principles of training. Practical work with "deep" NNs. Sequential variants of NN. AI applications.

Language of instruction

Czech

Number of ECTS credits

Mode of study

Not applicable.

Guarantor

doc. Ing. Lukáš Burget, Ph.D.

Department

Department of Computer Graphics and Multimedia (UPGM)

Entry knowledge

Not applicable.

Rules for evaluation and completion of the course

Half-semestral exam (20pts)
Three homework assignments (20pts)
Semestral exam, 60pts, requirement of min. 20pts.

Aims

Make students acquainted with the basics of artificial intelligence (AI) and machine learning (ML) that are the basic components of modern scientific methods, industrial systems and end-user applications - for example self-driving cars, cognitive robotics, recommendation systems, recognition of objects in images, chat-bots and many others. Show traditional techniques linked to currently dominating deep neural networks. Introduce basic mathematical formalism of AI and ML, that can be developed in specialized courses. Give an overview of software tools for AI and ML.

Students will:

get familliar with basic nomenclature of machine learning, esp. of modern neural networks
understand the relation between a task, a model and the process of learning
review classical search-based methods of artificial intelligence and will see the possibilities of combining them with machine learning
get familliar with basic machine learning models (gaussian models, gaussian classifiers, linear regression, logistic regression)
get familiar with modern neural networks for solving different tasks (classification, regression, tasks in reinforcement learning scenarios) on various kinds of data (unstructured, image, text, audio) and with methods of their training

Study aids

Not applicable.

Prerequisites and corequisites

Not applicable.

Basic literature

Not applicable.

Type of course unit

Lecture

26 hod., optionally

Teacher / Lecturer

Ing. Michal Hradiš, Ph.D.
doc. Ing. Lukáš Burget, Ph.D.
Ing. Karel Beneš, Ph.D.
Ing. Martin Dočekal

Syllabus

Introduction to artificial intelligence, machine learning and their relation
Basic tasks of machine learning (ML) - detection, classification, regression, prediction, sequence recognition, metrics for quality assessment.
Probabilistic approach to classification and recognition - basics of Bayes theory.
Gaussian model, its interpretation and training, PCA.
Linear and logistic regression, Support vector machines - basic formulation and kernel trick.
Neural networks (NN) - basic building blocks, principles of training.
Practical work with deep NNs - mini-batch, normalization, regularization, randomization, data augmentation.
Image processing variants of NN: convolutional architectures, information aggregation, very deep networks
Sequentional variants of NN: RNN, LSTM, BLSTM, autoencoders, attention models, use of NN embeddings.
Reinforced learning with NNs and without them
State space search, game playing
Local search, constraint satisfaction problems
AI applications.

Seminar

13 hod., optionally

Teacher / Lecturer

Ing. Michal Hradiš, Ph.D.
Ing. Karel Beneš, Ph.D.
doc. Ing. Lukáš Burget, Ph.D.

Syllabus

Lectures will be immediately followed by demonstration exercises (1h weekly) where examples on data and real code in Python will be presented. Code and data of all demonstrations will be made available to the students.

Project

13 hod., optionally

Teacher / Lecturer

Ing. Karel Beneš, Ph.D.

Syllabus

The subject includes three homework assignments:

Data modelling and simple classifiers
Construction of a simple neural network
Problem solving by search

Elearning

eLearning: currently opened course

VUT

Faculties

University Institutes

Parts

Artificial Intelligence and Machine Learning

Type of course unit