The course introduces students to the theoretical foundations of machine learning and data science, as well as to the solution of real business problems with the help of computer vision, classification and regression algorithms. The optimal balance between theory and practice provides both a good foundation and the ability to apply knowledge in practice.
Online lectures will be delivered synchronized as live talk with professors and groupmates. Records of classes will be available on SPbPU platform for 1 month after the course end.
Duration: 2 weeks ECTS credits: 4.0 Participation fee: Online format: 270 Euro Hybrid format: 270 Euro + 4000 Rub (non-refundable registration fee for the Letter of Invitation)
Participation fee includes tuition fee, study materials, field trips and cultural program.
Upon successful completion of the course students will receive hard copies of certificates with ECTS credits (mailed by post in case of the online format of the Winter School).
Online format:* - Online Pub Quiz; - Online Interactive Tour to SPbPU Museum; - Online broadcasting of excursion to the Hermitage museum; Cultural program in the Hybrid format is discussed with participants individually.
*All of the listed above activities are planned to take place but in case any of those will have to be cancelled, an alternative event will be offered to participants.
Accommodation Provided only for the Hybrid or the Tailor-made formats: on campus at the university dormitory off-campus at partner hostels in the city center
Details of the options and booking procedures will be discussed with each applicant individually.
Deadline for registration Online format: December 22, 2021 Hybrid format:
- for EU- or visa-free countries nationals: December 01, 2021
- for non-EU nationals: November 01, 2021
If you have taken the Data Analytics interseasonal course, there are no entrance requirements for you but the last two ones.
- Elementary knowledge of programming skills; - Knowledge of basics of matrix operations and differentiation; - Good command of English. All classes and extracurricular activities are carried out in English. Knowledge of the Russian language is not required; - Applicants are expected to have at least 1 year of University level studies.
The following topics will be covered:
- Introduction to Artificial intelligence and Machine Learning; - Brief History rewiew and state of the art; - Supervised and unsupervised learning; - Overfitting and underfitting; - Regularization in ML; - Model Validation techniques; - Machine learning algorithms classification; - Data processing techniques; - Machine learning application workflow; - Hyperparameters tuning tactiques; - Binary classification and logistic regression; - Shallow Neural networks; - Deep Neural networks; - Convolutional Neural Networks Basics; - Deep Sequential Neural Networks. The detailed course description for ECTS credits transfer at your home university: Machine Learning: Theory and Application.pdf
Professors and lecturers: Ogul Unal - PhD, Institute of Computer Science and Technology, SPbPU; M-com Search Engine Optimization specialist”; Nikita Kudryashov – PhD, Institute of Computer Science and Technology, SPbPU; Gazprom-neft leading specialist. Contacts: Summer and Winter Schools Team