Master 2021/2022

Machine Learning and Data Mining

Category 'Best Course for Career Development'

Type: Elective course (Data Science)

Area of studies: Applied Mathematics and Informatics

Delivered by: School of Data Analysis and Artificial Intelligence

Where: Faculty of Computer Science

When: 1 year, 1, 2 module

Mode of studies: offline

Open to: students of all HSE University campuses

Instructors: Artem Maevskiy, Alexander Rogachev

Master’s programme: Data Science

Language: English

ECTS credits: 4

Contact hours: 56

Course Syllabus

Abstract

The course "Machine Learning and Data Mining"; introduces students to new and actively evolving interdisciplinary field of modern data analysis. Started as a branch of Artificial Intelligence, it attracted attention of physicists, computer scientists, economists, computational biologists, linguists and others and become a truly interdisciplinary field of study. In spite of the variety of data sources that could be analyzed, objects and attributes that from a particular dataset poses common statistical and structural properties. The interplay between known data and unknown ones give rise to complex pattern structures and machine learning methods that are the focus of the study. In the course we will consider methods of Machine Learning and Data Mining. Special attention will be given to the hands-on practical analysis of the real world datasets using available software tools and modern programming languages and libraries.

Learning Objectives

• To familiarize students with a new rapidly evolving filed of machine learning and mining, and provide practical knowledge experience in analysis of real world data.

Expected Learning Outcomes

• Students derive the bias-variance decomposition for MSE and “0-1” losses, and show how regularization affects the tradeoff.
• Students explain the main approaches to graphical probabilistic models and training of them.
• Students explain the relation between linear models and deep neural networks, describe how neural networks are trained, and understand what the role of data scientist is in designing a deep learning solution to a machine learning problem.
• Students know meta-learning approaches.
• Students know the statement of No-Free-Lunch theorems and explain the role of prior knowledge for solving machine learning problems.
• Students understand the principles behind Variational AutoEncoders and implement them.
• Students understand the principles of Generative Adversarial Networks, know which metrics they can optimize and how to regularize them.
• Students use the techniques for working with imbalanced datasets.
• Students explain and utilize the black-box optimization techniques.
• Students explain the concepts of bootstrapping, bagging and boosting, and justify the choice of a particular weak learner for a given aggregating algorithm.

Course Contents

• Introduction to Machine Learning and Data Mining, No-Free-Lunch theorems
• Bias-variance decomposition, regularization techniques
• Introduction to meta-algorithms, bootstrap, boosting
• Introduction and overview of deep learning methods
• Deep generative models: Generative Adversarial Networks (GANs)
• Optimization techniques: black-box methods, first order methods
• Miscellaneous topics: imbalanced datasets, importance sampling, one-class classification methods
• Deep generative models: energy-based models, Boltzmann machines and deep belief networks
• Deep generative models: Variational AutoEncoders
• Meta-learning: concept learning, learning how to learn

Assessment Elements

• Homeworks
• Exam

Interim Assessment

• 2021/2022 2nd module
  Final score for the homework:
  homework score = min [1, ∑_ix_i] - penalty, where x_i is a score for each homework.
  
  (Final grade) = 50% × (homework score) + 50% × (exam score).

  • since each homework has a max score of 1 and there are 3 assignments, it will be scaled by 5/3 in this formula;
  • max exam score is 10, so it will be scaled by 1/2.

  
  Final grade = [5/3 ⋅ homework score + 1/2 ⋅ exam score]

Bibliography

Recommended Core Bibliography

• Hall, M., Witten, Ian H., Frank, E. Data Mining: practical machine learning tools and techniques. – 2011. – 664 pp.
• Han, J., Kamber, M., Pei, J. Data Mining: Concepts and Techniques, Third Edition. – Morgan Kaufmann Publishers, 2011. – 740 pp.
• Hastie, T., Tibshirani, R., Friedman, J. The elements of statistical learning: Data Mining, Inference, and Prediction. – Springer, 2009. – 745 pp.

Recommended Additional Bibliography

• Mirkin, B. Core concepts in data analysis: summarization, correlation and visualization. – Springer Science & Business Media, 2011. – 388 pp.