• HOME
• ABOUT US
  • Name Address
  • General Description
  • Governance
  • Academic Calendar
  • Degree Programmes
  • List of Programmes in English
  • General Admission and Registration Procedures
  • Credit Mobility and Recognition of Prior Learning
  • ECTS Credit Allocation
  • Academic Guidance
  • Contacts
• Degree Programmes
  • Third Cycle Programmes (Doctorate Degree)
  • Second Cycle Programmes (Master's Degree)
  • First Cycle Programmes (Bachelor's Degree)
  • Short Cycle Programmes (Associate's Degree)
• GENERAL INFORMATION FOR STUDENTS
  • Cost of Living
  • Accommodation
  • Meals
  • Medical Facilities
  • Facilities for Disabled Students
  • Insurance
  • Financial Supports
  • Student Affairs Office
  • Practical Information for International Students
  • Language Courses
  • Work Placement Possibilities
  • Sports, Social and Cultural Facilities
  • Student Associations and Clubs
  • About İzmir - Turkey
• INTERNATIONAL RELATIONS
  • International Relations Office
  • Registration Procedures
  • Agreements
  • Coordinators
  • Documents
  • List of Programmes in English
  • ECTS / DS Labels

Description of Individual Course Units

Course Unit Code Course Unit Title Type Of Course D U L ECTS MAT 4077 MATHEMATICS FOR MACHINE LEARNING I ELECTIVE 4 0 0 7

Offered By

Mathematics

Level of Course Unit

First Cycle Programmes (Bachelor's Degree)

Course Coordinator

PROFESSOR DOCTOR SELÇUK DEMIR

Offered to

Mathematics

Course Objective

The aim of this course is to learn basic mathematical background which are necessary for machine learning.

Learning Outcomes of the Course Unit

1   Will be able to learn the basic concepts of linear equation systems and matrices which are necessary for machine learning. 2   Will be able to use concepts such as vector spaces, norms, inner products, orthogonal projections, matrices, matrix decomposition and matrix approach which are necessary for machine learning. 3   Will be able to calculate partial derivatives, higher order derivatives, gradients and multivariable Taylor series. 4   Will be able to learn basic optimization methods used in machine learning. 5   Will be able to have knowledge about data, models and basics of learning. 6   Will be able to produce basic machine learning models.

Mode of Delivery

Face -to- Face

Prerequisites and Co-requisites

None

Recomended Optional Programme Components

None

Course Contents

Week Subject Description 1 Systems of linear equations, matrices, solving systems of linear equations. 2 Vector spaces, linear independence, linear mappings, affine spaces. 3 Norms, inner products, orthogonal basis, inner product of functions, orthogonal projections, rotations. 4 Determinants and traces, eigenvalues and eigenvectors, matrix decompositions, matrix approximations. 5 Partial differentiation and gradients, gradients of matrices, higher-order derivatives. 6 Linearization and multivariate Taylor series. 7 Probability spaces, discrete and continuous probabilities. 8 Midterm. 9 Bayes theorem, Gaussian distribution, change of variables, inverse transform. 10 Optimization using Gradient descent. 11 Constrained optimization and Lagrange Multipliers, convex optimization. 12 Data, models, and learning. 13 Empirical risk minimization, parameter estimation. 14 Probabilistic modelling and inference, directed graphical models, model selection.

Recomended or Required Reading

Textbook(s): Deisenroth, M. P., Faisal, A. A., Ong, C. S., Mathematics for Machine Learning, Cambridge University Press, 2020.

Planned Learning Activities and Teaching Methods

Lecture notes, presentation, problem solving.

Assessment Methods

SORTING NUMBER SHORT CODE LONG CODE FORMULA 1 MTE MIDTERM EXAM 2 ASG ASSIGNMENT 3 FIN FINAL EXAM 4 FCG FINAL COURSE GRADE MTE * 0.30 + ASG * 0.30 + FIN * 0.40 5 RST RESIT 6 FCGR FINAL COURSE GRADE (RESIT) MTE * 0.30 + ASG * 0.30 + RST * 0.40 *** Resit Exam is Not Administered in Institutions Where Resit is not Applicable.

Further Notes About Assessment Methods

None

Assessment Criteria

To be announced.

Language of Instruction

English

Course Policies and Rules

To be announced.

Contact Details for the Lecturer(s)

selcuk.demir@deu.edu.tr

Office Hours

To be announced.

Work Placement(s)

None

Workload Calculation

Activities Number Time (hours) Total Work Load (hours) Lectures 13 4 52 Preparations before/after weekly lectures 13 4 52 Preparation for midterm exam 1 24 24 Preparation for final exam 1 24 24 Preparing assignments 1 8 8 Midterm 1 3 3 Final 1 3 3 Project Assignment 1 0 0 TOTAL WORKLOAD (hours) 166

Contribution of Learning Outcomes to Programme Outcomes

PO/LO PO.1 PO.2 PO.3 PO.4 PO.5 PO.6 PO.7 PO.8 PO.9 PO.10 PO.11 PO.12 PO.13 LO.1 5 5 5 4 5 5 4 LO.2 5 5 5 4 5 5 4 LO.3 5 5 5 4 5 5 4 LO.4 5 5 5 4 5 5 4 LO.5 5 5 5 4 5 5 4 LO.6 5 5 5 4 5 5 4