Code: E371076 |
Artificial Intelligence and Neural Networks in Applications |
Lecturer: prof. RNDr. Olga Štěpánková CSc. |
Weekly load: 2P+2C |
Completion: A, EX |
Department: 12110 |
Credits: 5 |
Semester: W |
- Description:
-
Students will learn about basic problems in the field of artificial intelligence and methods of solving them. The content of the course is: State space, its search methods and their complexity; Genetic algorithms; Basic machine learning algorithms; Clustering; Learning from classified data; Combination of classifiers; Fundamentals of formal propositional and predicate logic as problem solving tools; Automatic theorem proving - resolution method; Neural networks (MLP, CNN, RNN, LSTM), Deep learning.
- Contents:
-
1. What is the purpose of AI, what AI can do now and what impact it has on society.
2. State space and methods for solving typical problems.
3. State space - search complexity and how to face it.
4. Genetic algorithms 1
5. Genetic algorithms 2
6. Machine learning and its basic algorithms. Clustering.
7. Learning from classified data. Combination of classifiers.
8. Problem solving theory and the use of formal logic.
9. Propositional and predicate logic
10. Automatic theorem proving-resolution method
11. Neural networks, theories, perceptron, MLP
12. Deep learning, convolutional neural networks, influence of architecture
13. Neural networks for natural language processing, RNN, LSTM; Transformers.
- Seminar contents:
-
The topics of the seminaries follow the topics of lectures.
Conditions for the assessment:
Credit Conditions:
- Active Participation: Attend at least 70% of the labs.
- Submission of Assignments: Submit 3 out of 5 assigned individual until the deadline 14 days from the beginning of the examination period.
- During the semester, a total of 5 individual tasks from various topics covered in the curriculum will be assigned during the labs.
- Students have 14 days to submit each task. If an assignment is submitted on time, the student can earn the maximum number of points for that task.
- The maximum points decrease by 1 point per day of delay beyond the submission deadline, until it reaches 0 points.
- These earned points contribute to the overall evaluation for the final exam.
- Recommended literature:
-
1. Russel, Stuart and Norvig, Peter (2022 ? the 4th edition) (parts of chapters 2, 3, 6, 7, 10, 18). Artificial Intelligence: A Modern Approach (Prentice Hall, 1995 ? the 1st edition), ISBN 978-0134610993.
2. Mitchell, Melanie (1996). An Introduction to Genetic Algorithms. Cambridge, MA: MIT Press. ISBN 9780585030944
3. Ian Goodfellow, Yoshua Bengio, Aaron Courville, Deep Learning. MIT Press, 2016. [online] Available: https://www.deeplearningbook.org/
- Keywords:
- Theory of problem solving, formal logic, formal grammars, fuzzy controllers, genetic algorithms, neural networks.
Abbreviations used:
Semester:
- W ... winter semester (usually October - February)
- S ... spring semester (usually March - June)
- W,S ... both semesters
Mode of completion of the course:
- A ... Assessment (no grade is given to this course but credits are awarded. You will receive only P (Passed) of F (Failed) and number of credits)
- GA ... Graded Assessment (a grade is awarded for this course)
- EX ... Examination (a grade is awarded for this course)
- A, EX ... Examination (the award of Assessment is a precondition for taking the Examination in the given subject, a grade is awarded for this course)
Weekly load (hours per week):
- P ... lecture
- C ... seminar
- L ... laboratory
- R ... proseminar
- S ... seminar