VIK004 Machine Learning

Faculty of Arts
Spring 2002
Extent and Intensity
2/0/0. 3 credit(s). Type of Completion: k (colloquium).
Teacher(s)
doc. Ing. Jan Žižka, CSc. (lecturer)
Guaranteed by
PhDr. Pavla Kánská
Department of Machine Learning and Data Processing – Faculty of Informatics
Contact Person: Mgr. Martina Sendlerová
Course Enrolment Limitations
The course is only offered to the students of the study fields the course is directly associated with.

The capacity limit for the course is 40 student(s).
Current registration and enrolment status: enrolled: 0/40, only registered: 0/40
fields of study / plans the course is directly associated with
Syllabus
  • Machine Learnig (ML) as the integration of Artificial Intelligence (AI) and cognitive sciences. Computational processes that are related to learning. Selection of learning algorithms.
  • Training and testing data. Solution space. Learning and searching. Natural and human learning. Problem representation language. Learning algorithms with numerical and symbolic inputs.
  • Perceptrons, logical neural networks, Boltzmann machine, Kohonnen maps. Genetic algorithms. Comparison with biological systems.
  • Methods of decision-tree induction. Presence of noise, incomplete description of examples. Utilization of knowledge and the possibility of transformation from decision trees to rules.
  • Pattern recognition. Generalisation. The method of a nearest neighbour (k-NN). Instance-based learnig (IBL). Radial basis functions (RBF).
  • Learning in rule-based systems. Inductive and EBL (deductive) learning.
  • Other learning methods. Reinforcement learning.
  • Mathematical aspects of learning. PAC, VC-dimension, Occam's razor.
Language of instruction
Czech
The course is also listed under the following terms Autumn 2001, Spring 2003, Spring 2004.
  • Enrolment Statistics (Spring 2002, recent)
  • Permalink: https://is.muni.cz/course/phil/spring2002/VIK004