Mathematical Principles of AI - Opinto-opas

The participant will learn the mathematical methods behind most common machine learning models and learn how to apply them in the development of AI-based applications. He/she will know several optimisation methods to find the optimal solution and will be able to justify the choice in a given situation. After completing the course, the participant will be able to work independently in the development of models for AI applications and apply the available knowledge in model building.

- master the mathematical methods underlying machine learning models

- be able to develop Python-based solution models for optimisation problems in machine learning

- be able to apply data collected from information systems to model building

- understand the role of mathematical models in different parts of neural networks

This course unit is part of the master's degree's curriculum. Completion of the course requires master's study entitlement.

Mathematical models for applied artificial intelligence

- One and several variable differential and integral calculus

- Basics of linear algebra: vectors, matrices

- Regression models

- Different numerical methods for optimisation

- Symbolic and numerical calculations based on Python programming language

- Neural networks

Student is be able to perceive the key concepts of machine learning mathematics. He/she will be able to perform individual tasks related to the calculation of key concepts. Student can also apply their learning in practice to some extent.

When the implementation type of the course is CONTACT, ONLINE or BLENDED it is required that the student is present during those teaching hours that are marked in the study schedule. If you are absent more than 25 %, your grade will be lowered by one. If you are absent more than 50 %, the course is failed.

Student can model computations in machine learning problems at a basic conceptual level. He/she is able to carry out planning and controlling calculations to develop the models and to calculate related assessment calculations. Student can also apply calculations to practical situations.

Student has a deep understanding of the mathematical concepts of machine learning models and he is able to seamlessly perform calculations for AI applications. He/she is able to extensively apply the learned skills to problems in machine learning and to independently perform related calculations. Student is also able to interpret the solutions of the calculations for interest groups. The student will also be very good at applying his/her learning to practical computational situations.

This course implementation has lessons every week. The lessons include relevant mathematical principles and the use of Python in calculations. Some of the lessons are intended to the guidance of course assignments. In particular, for each course assignment before the submission date there is an associated lecture.

The course implementation welcomes independent study of topics, e.g. by means of examples in the course material, within the framework of the Haaga-Helia University of Applied Sciences' guidelines.

No previous experience in coding is required.

Lili Aunimo

The learning material is mainly distributed through the Moodle learning environment. The course brings together key mathematical concepts related to the applications of AI. It also provides tools for applied analytics research and thesis work. Such issues are constantly evolving and the course will make use of material produced by the course teachers and otherwise up-to-date material.

The course implementations are designed for students who are about to enter work life or are already working there. The course content takes into account the content used in the field.

Pasila Campus

The exam will be held at the end of the course on a date to be mutually agreed upon participants during the course. The date of the re-examination will also be agreed together during the implementation.

In all exams and retakes participant must be present in Pasila, where the identity of the examiner will be verified.

In the case of examinations, the participant has restricted access to some materials and coding environment. It is therefore not possible to conduct the test as in electron exam facilities (Exam).

English

Mathematical and methodological skills are international skills.

13.01.2025 - 16.05.2025

The topics presented in the course lectures are learned by doing related exercises. Assignments will be returned regularly throughout the course. The learning tasks will practice the use of applications of mathematical concepts and their calculation using the Python programming language.

07.01.2025 - 10.01.2025

The course has weekly lessons according to the timetable. A detailed weekly timetable will be made available on the Moodle learning environment if the Director of Studies decides to starts this implementation. The timetable for the returnable learning assignments will follow the lecture timetable.

MAAIBUME
CONTACT

There are no shortcuts to learning, and doing the work is essential. Other ways to get your grade in the Haaga-Helia University of Applied Sciences' register of credits should be inquired from the teacher responsible for the course.

Juha Nurmonen, Toni Ernvall

15 - 30

The learning assignments account for 40% of the final grade and the exam for 60%.

AIBUM Degree Programme in AI for Business Transformation

0.00 cr

H-5