Machine Learning Algorithms Field of study: Computer Science
Programme code: 08-S2INIA15.2016

Module name: Machine Learning Algorithms
Module code: 08-IN-IJO-S2-AUM
Programme code: 08-S2INIA15.2016
Semester: summer semester 2016/2017
Language of instruction: English
Form of verification: exam
ECTS credits: 4
Description:
Lecture is destined for IT students. Its aim is to familiarize the students with algorithms of machine learning. Presented will be various methods of learning with supervision and without it with special emphasis on reinforced learning methods Using time differences in reinforcements updates is to be verified in application prepared by the students, dedicated to artificial life technology.
Prerequisites:
(no information given)
Key reading:
(no information given)
Learning outcome of the module Codes of the learning outcomes of the programme to which the learning outcome of the module is related [level of competence: scale 1-5]
Is able to work in several person team and properly divide tasks into subtasks. [AUM _K10]
 K_2_A_I_K03 [1/5] K_2_A_I_K04 [1/5] K_2_A_I_K05 [1/5]
Can independently formulate a problem. [AUM _U09]
 K_2_A_I_U01 [1/5]
Can use the methods and formalized models to modeling tasks and algorithms of machine learning, including techer=?participated and unsupervised learning in IT systems and in software. [AUM _U5]
 K_2_A_I_U01 [1/5] K_2_A_I_U13 [1/5] K_2_A_I_U15 [1/5] K_2_A_I_U16 [1/5]
Can assess utility of various paradigms and machine learning methods and programming environments connected with them to solve practical conceptual and technical problems of different types. [AUM _U6]
 K_2_A_I_U01 [1/5] K_2_A_I_U08 [1/5] K_2_A_I_U10 [1/5] K_2_A_I_U15 [1/5]
Is able to construct algorithms using algorithmic techniques from the field of machine learning, including symbolic and numeric representations. [AUM _U7]
 K_2_A_I_U04 [1/5] K_2_A_I_U15 [1/5] K_2_A_I_U16 [1/5] K_2_A_I_U17 [1/5]
Can analyse facultative system concerning appropriately used machine learning algorithm. [AUM _U8]
 K_2_A_I_U08 [1/5] K_2_A_I_U10 [1/5] K_2_A_I_U15 [1/5] K_2_A_I_U16 [1/5]
Has knowledge in the field of mathematics covering linear algebra, elements of probability calculus, discrret mathematics and numerical methods necessary to modeling problems in the sphere of machine learning. [AUM _W1]
 K_2_A_I_W01 [1/5] K_2_A_I_W02 [1/5] K_2_A_I_W03 [1/5]
Has widened knowledge about various paradigms, methods and algorithms of machine learning, including teacher?participated learning and unsupervised learning. [AUM _W2]
 K_2_A_I_W01 [1/5] K_2_A_I_W09 [1/5] K_2_A_I_W12 [1/5] K_2_A_I_W14 [1/5]
Has deepened and structured knowledge in the field of programming in declarative, imperative and functional programming languages used to implement machine learning algorithms. [AUM _W3]
 K_2_A_I_W01 [1/5] K_2_A_I_W09 [1/5] K_2_A_I_W10 [1/5] K_2_A_I_W18 [1/5]
Understands the current state and newest achievements and IT developmental trends including artificial intelligence, artificial life and methods of machine learning in the areas of their use in IT and technology. [AUM _W4]
 K_2_A_I_W14 [1/5] K_2_A_I_W17 [1/5] K_2_A_I_W18 [1/5]
Type Description Codes of the learning outcomes of the module to which assessment is related
Exam [AUM _w_1]
Solving tasks of content, one after each section discussed during the lecture.
 AUM _W1 AUM _W2 AUM _W3 AUM _W4
Control tests [AUM _w_2]
Tests after each topic discussed during classes including control of theoretical knowledge from the lecture.
 AUM _U5 AUM _U6 AUM _U7 AUM _U8
Group reports [AUM _w_3]
Solving tasks given in thematic sets, grouped into 5, 7 tasks in each set.
 AUM _K10 AUM _U09
Form of teaching Student's own work Assessment of the learning outcomes
Type Description (including teaching methods) Number of hours Description Number of hours
lecture [AUM _fs_1]
Presenting educational content in verbal form, using content visualization. Focusing on conceptually complex material and indicating additional material – own elaborations. These will constitute basis for credit tests.
 30
Familiarizing with lecture content using the existing methods packets: individual elaborations, websites.
 20 Exam [AUM _w_1]
laboratory classes [AUM _fs_2]
Students get acquainted with mathematical models of machine learning and solve tasks from this field.
 30
Solving tasks of subsequent topics together with the existing solutions analyses – in elaborations and on websites. Analysis and electronic description of the learning system, it s verification in an environment specified by the teacher.
 30 Control tests [AUM _w_2] Group reports [AUM _w_3]
Attachments
Module description (PDF)
Information concerning module syllabuses might be changed during studies.
Syllabuses (USOSweb)
Semester Module Language of instruction
(no information given)