DS213BKK
Practical Machine Learning
Faculty Profiles
Mikhail Romanov
Senior Machine Learning Engineer, Yandex, Expert
Andrei Nartsev
Senior Machine Learning Engineer at Yandex
Course length
Duration
Total hours
Credits
Language
Course type
Fee for single course
Fee for degree students
Skills you’ll learn
Overview
In practice, machine learning specialists solve a wide scope of tasks, such as: formulating business problems in terms of machine learning, data collection and preprocessing, models training and validation, deploying models in production, monitoring the quality of the models, etc. In this course, students will go through each of these sections, consider the problems that arise in practice, and study the necessary tools for solving them. The students will then develop a project on one of the applied tasks of machine learning aimed at consolidating the acquired knowledge.
Learning highlights
- How to properly organize work at each step of the development of machine learning models in practice.
- How to formulate business problems in terms of machine learning.
- How to implement MLOps pipelines for collecting data and training models.
- How to deploy machine learning models in production.
- How to control model quality and validate regular retraining models.
Course outline
15 classes
Session 1
Introductory lecture: сourse objectives, discussion of projects.
Formulating a business problem in terms of machine learning.
Key steps for the implementation of machine learning models in practice.
Session 2
Data preparation: collection and preprocessing.
Main types of web scraping and crawling and tools we can apply.
The major steps of data preprocessing.
Session 3
Embeddings.
Kinds of embedding techniques.
Evaluating quality of embeddings and visualisation.
Algorithms for efficient search in embedding space.
Session 4
Machine Learning in applications: information retrieval.
Problem statement. Metrics and loss functions.
Multi-stage ranking.
Practical cases.
Session 5
Machine Learning in applications: recommender systems.
Problem statement. User-based and content-based approaches.
The problem of diversity in recommender systems.
Practical cases.
Session 6
Machine Learning in applications: text summarization.
Problem statement. Summarization quality metrics.
Solution methods: from classical algorithms to transformers.
Practical cases.
Session 7
Chatbot development.
Tools for chatbot implementation and deployment.
Designing proper system architecture.
Session 8
MLOps pipelines.
Pipeline for collecting data, training and deploying models.
Online learning and regular retraining of models.
Session 9
Tuning ML Models.
Methods for hyperparameters selection. Offline quality control (validation based on historical data).
Online quality control (A/B testing).
Session 10
ML models in production.
Deployment of ML models. Docker. ML storage. Validating regular retraining models. Monitoring and alerting. Grafana.
Prometheus.
Session 11
Supervision of collaborative work on a project.
Session 12
Supervision of collaborative work on a project.
Session 13
Supervision of collaborative work on a project.
Session 14
Mock project presentation.
Session 15
Project presentation.
Prerequisites
It is highly recommended to have attended the courses linked below. Although if any of these courses were not completed, it will not prevent a student from attaining the current one, but the following skills are absolutely necessary:
Strong programming background (Python).
Understanding of classical machine learning concepts and algorithms.
Experience with Deep Learning models for Natural Language Processing.
Python for ML
Oct 03 - Oct 21, 2022
Anier Velasco Sotomayor
Lead at the ML Theory group at Cohere for AI Open Science community.
Machine Learning in Applications for Text Mining
Jan 09 - Jan 27, 2023
Sergey Khoroshenkikh
Senior Software Engineer at Yandex
Capstone Project Kick-off
Jan 30 - Feb 17, 2023
Anna Chuvilina
Self Employed Analyst
Intro to Deep Learning
May 08 - May 26, 2023
Mikhail Romanov
Senior Machine Learning Engineer, Yandex, Expert
Methodology
The course is focused on practical machine learning methods and tools, yet providing a necessary theoretical and algorithmic background. During the course, students will choose an applied machine learning problem, explore it, and present the results of the research in the final session. As part of the project work, it will be necessary to implement the training pipeline and integrate the model into a real-time service.
The course will be organized in three-hour sessions and self-study practical assignments. Sessions will contain both theoretical and practical parts with different ratios depending on the materials.
Grading
Mikhail Romanov, PhD, is a deep learning researcher and engineer. His experience includes deep learning for production, scientific computing and research, accompanied by teaching mathematics and machine learning in general.
His academic experience includes teaching courses at MIPT, HSE, Harbour Space Universities and online platforms. As a researcher, he has conducted research at the Technical University of Denmark, Mail.ru, Samsung Research, Quantori, and Yandex. In his research, his main areas of interest are depth estimation, optical flow, optimisation of neural networks, multi-task learning, self-supervised learning, LLMs and diffusion models. He has published papers on tomography, deep learning, scientific computing, computer vision, generative AI, and diffusion models.
See full profileAndrei Nartsev is a senior machine learning developer whose core interests are classical ML models and Deep Learning. He has experience in managing a team of ML developers in advertisement. He was developing automated bidding algorithms and now focuses on marketplace management algorithms for Yandex Delivery.
Andrei participated in several ICPC contests and obtained prize-winning places including ICPC Northern Eurasia Finals 2019 and ICPC Northern Eurasia Finals 2020.
See full profileApply for this course
Practical Machine Learning
by Mikhail Romanov, Andrei Nartsev
Total hours
45 Hours
Dates
May 29 - Jun 16, 2023
Fee for single course
€1500
Fee for degree students
€750
Fundamentals of Operating Systems
Mar 13 - Mar 30, 2023
Konstantin Yegupov
Core Engineer at CausalApp Ltd.
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.