Faculty of Information Technology, BUT

Course details

Artificial Intelligence and Machine Learning

SUI Acad. year 2019/2020 Winter semester 5 credits

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.

Guarantor

Deputy Guarantor

Language of instruction

Czech

Completion

Examination (written)

Time span

26 hrs lectures, 13 hrs exercises, 13 hrs projects

Assessment points

51 exam, 20 half-term test, 14 exercises, 15 projects

Department

Lecturer

Instructor

Beneš Karel, Ing. (DCGM FIT BUT)
Fajčík Martin, Ing. (DCGM FIT BUT)
Šůstek Martin, Ing. (DITS FIT BUT)

Learning objectives

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.

Why is the course taught

Artificial intelligence (AI) and machine learning (ML) are nowadays spread from expected places (Google, Facebook) to recommendation systems in e-shops, games, search for travel itineraries, camera focusing, and many others. SUI course provides a basic overview of algorithms and applications of AI and ML for all students of the master program at FIT, and thus fulfills the "AI" in its title. After SUI, artificial neural networks and other components of ML and AI system wont be "magical black boxes" anymore. You will know the basis they are build around - for many of you, this information will be sufficient; those interested can go deeper in specialized courses.

Study literature

  • C. Bishop: Pattern Recognition and Machine Learning, Springer, 2006 
  • Russel,S., Norvig,P.: Artificial Intelligence, Prentice-Hall, Inc., third edition 2010, ISBN 0-13-604259-7 
  • Ertel, W.: Introduction to Artificial Intelligence, Springer, second edition 2017, ISSN 1863-7310 
  • Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, 2016.

Fundamental literature

  • C. Bishop: Pattern Recognition and Machine Learning, Springer, 2006 
  • Russel,S., Norvig,P.: Artificial Intelligence, Prentice-Hall, Inc., third edition 2010, ISBN 0-13-604259-7 
  • Ertel, W.: Introduction to Artificial Intelligence, Springer, second edition 2017, ISSN 1863-7310 
  • Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, 2016.

Syllabus of lectures

  1. Introduction, overview of methods for solving AI tasks, including game playing. 
  2. Logic and its use in task solving and planning.  
  3. PROLOG vs. AI. 
  4. Basic tasks of machine learning (ML) - detection, classification, regression, prediction, sequence recognition, metrics for quality assessment.  
  5. Basic approaches to ML - decision trees, version spaces, reinforcement learning, active learning. 
  6. Probabilistic approach to classification and recognition - basics of Bayes theory. 
  7. Gaussian model, its interpretation and training, PCA. 
  8. Linear and logistic regression, Support vector machines - basic formulation and kernel trick.  
  9. Neural networks (NN) - basic building blocks, principles of training.
  10. Practical work with deep NNs - mini-batch, normalization, regularization, randomization, data augmentation.  
  11. Sequentional variants of NN: RNN, LSTM, BLSTM, autoencoders, attention models, use of NN embeddings. 
  12. AI applications 1. 
  13. AI applications 2.

Syllabus of numerical exercises

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 and will constitute the basis for two homeworks solved during the semester.

Syllabus - others, projects and individual work of students

The project is assigned in combination with another master course based on students specialization. It is solved in teams of up to 5 students. The goal is to solve a problem using an AI or ML technique, data and auxiliary functions (for example for feature extraction) will be provided. Examples of projects: 
  1. recognition of object in image. 
  2. keyword detection 
  3. prediction of currency exchange rate 
  4. detection of sentiment from text 
  5. estimation of liveness of tissue from bloodstream image.

Progress assessment

  • Solving and submitting solution of two home-works during the semester (7pts each, total 14pts) 
  • Half-semestral exam (15pts)  
  • Submission of project (20pts) 
  • Semestral exam, 51pts, requirement of min. 17pts.

Schedule

DayTypeWeeksRoomStartEndLect.grpGroupsInfo
Monlecturelectures E104 E105 E112 08:0009:50 1MIT 2MIT xx
Monexerciselectures E104 E105 E112 10:0010:50 1MIT 2MIT xx

Course inclusion in study plans

Back to top