DS405
Master's Machine Learning
Faculty
Iurii Efimov
Principal R&D Engineer at Geotab
Course length
Duration
Total hours
Credits
Language
Course type
Fee for single course
Fee for degree students
Skills you’ll learn
Overview
The course aims to provide a systematic introduction to modern machine learning models, starting from basic concepts and mathematical foundations and delving into deep aspects such as attention mechanisms in neural networks and geometric machine learning. The course covers the application of machine learning to various types of data, including text, images, time series, and others.
The course contains both sufficient theoretical material and practical seminars using datasets of different natures. The coursework involves implementing machine learning algorithms to consolidate understanding of the theory, as well as lab work to acquire skills of conducting full-cycle workflow. Upon successful completion, participants will be able to apply basic machine learning techniques in practice, explain the obtained results, and comfortably explore advanced courses in various machine learning areas.
The course is designed for technical professionals who seek a deep understanding of the structure of modern machine learning techniques. It is suitable for both beginners and practising specialists who wish to systematise and expand their knowledge in this area.
Learning highlights
- Know basic ML problem formulations.
- Know basic models of ML.
- Be able to choose the problem statement and mode for a particular situation.
- Know where to find datasets and readymade models for basic problems.
- Be able to perform basic data analysis before building the model.
- Be able to measure results of modelling and make conclusions from modelling.
Course outline
15 classes
Session 1
Introduction to Machine Learning; Nearest Neighbours algorithm; Basic Instruments in Python.
Session 2
Regression problem overview; Linear Models; Gradient descent; Naive implementation and sklearn usage.
Session 3
Classification. Logistic Regression. PyTorch Practice.
Session 4
PCA and kNN and PCA on images and kNN usage.
Session 5
Decision Trees; Information criteria.
Session 6
Ensembles; Bagging, Boosting.
Session 7
Hyperparameter optimisation.
Q&A Session & Mock ML interview questions.
Session 8
Midterm test.
Session 9
Neural Networks basics. NN practice with PyTorch
Session 10
NN Regularisation
Session 11
Convolutional Neural Networks. Sequence and Image processing.
Session 12
Language modeling. Recurrent Neural Networks. Markov property. Char-level Generation
Session 13
Embeddings, self-supervised and weekly supervised learning.
Session 14
Unsupervised learning. Clustering. Dimensionality reduction.
Session 15
Final test and outro.
Prerequisites
Basic maths knowledge: Linear algebra: vectors, dot products, linear functions, matrices, matrix decompositions Calculus: multidimensional functions, derivatives, gradients, matrix derivatives Optimisation: definition of optimisation problem, convex functions
Programming: Python: functions, classes, wrappers Libraries: numpy, scipy, pandas, matplotlib
Methodology
The course consists of lectures (with mostly theoretical stuff) and practical sessions with coding following each lecture. Classes are offline, and visiting is essential for successful course passing.
Each class you will have a small test to reinforce previous class knowledge and understanding.
There are three laboratory works that are required to be done by each student to create skills for making the whole pipeline of modelling.
Grading
Iurii Efimov is a Senior Research Engineer majoring in fields of modern AI applications for vision-related tasks. His research is focused on state-of-the-art cloud and edge AI methods for 2d and 3d signal processing. Also, Iurii is a Member of the core video intelligence team working on AI dashcams at Geotab. He has contributed to innovative features of the latest Geotab’s products. His academic studies and former industry experience are related to human biometric authentication and anti-spoofing for edge devices.
See full profileApply for this course
Master's Machine Learning
by Iurii Efimov
Total hours
45 Hours
Dates
Nov 30 - Dec 18, 2026
Fee for single course
€1500
Fee for degree students
€750
How to secure your spot
Complete the form below to kickstart your application
Schedule your Harbour.Space interview
If successful, get ready to join us on campus
FAQ
Will I receive a certificate after completion?
Yes. Upon completion of the course, you will receive a certificate signed by the director of the program your course belonged to.
Do I need a visa?
This depends on your case. Please check with the Spanish or Thai consulate in your country of residence about visa requirements. We will do our part to provide you with the necessary documents, such as the Certificate of Enrollment.
Can I get a discount?
Yes. The easiest way to enroll in a course at a discounted price is to register for multiple courses. Registering for multiple courses will reduce the cost per individual course. Please ask the Admissions Office for more information about the other kinds of discounts we offer and what you can do to receive one.