Modern Methods of Data Analysis

2021/2022

Academic Year

ENG

Instruction in English

8

ECTS credits

Delivered at:

Department of Applied Mathematics and Informatics (Faculty of Informatics, Mathematics, and Computer Science (HSE Nizhny Novgorod))

Course type:

Compulsory course

When:

1 year, 2 module

Instructor

Grechikhin, Ivan

Course Syllabus

Abstract

The course is devoted to the presentation of modern data analysis and machine learning methods that are widely used in computer vision. The main emphasis is placed on such sections as learning and inference in vision. A taxonomy of models that relate the measured image data and the actual scene content is studied. Generative and discriminative models Classification, regression and clustering methods.

Learning Objectives

• Mastering theoretical background of machine learning.
• Obtaining skills of the correct selection of methods for solving the problem

Expected Learning Outcomes

• Distinguish the main tasks of machine learning;
• Student will be able to process tabular data
• Apply dimensionality reduction to data
• Apply regularization to address overfitting
• Distinguish components of learning error
• Perform cluster analysis
• Successfully passed final assesment and TBD
• Train and validate decision tree models for classification
• Train and validate KNN model
• Train and validate linear models for classification and regression problems
• Train ensembles of models
• Train MLP for supervised learning taks
• Tune decision tree hyperparameters
• Understand core principles of artificial neural networks

Course Contents

• Introduction to Machine Learning
• Ensemble Learning
• Decision Trees
• Introduction to Artificial Neural Networks
• Linear Models
• Unsupervised Learning
• Final Task with instructor’s evaluation

Assessment Elements

• Tests (1-6 weeks)
• Programming Assignment (2 per course)
• Final project - applied practical problem to solve
  Staff graded assignment

Interim Assessment

• 2021/2022 2nd module
  0.4 * Programming Assignment (2 per course) + 0.4 * Final project - applied practical problem to solve + 0.2 * Tests (1-6 weeks)

Bibliography

Recommended Core Bibliography

• Computer vision : models, learning, and inference, Prince, S. J. D., 2012
• Core data analysis : summarization, correlation, and visualization, Mirkin, B., 2019
• Introduction to machine learning, Alpaydin, E., 2020
• Machine learning : a probabilistic perspective, Murphy, K. P., 2012
• Muller, A. C., & Guido, S. (2017). Introduction to machine learning with Python: a guide for data scientists. O’Reilly Media. (HSE access: http://ebookcentral.proquest.com/lib/hselibrary-ebooks/detail.action?docID=4698164)

Recommended Additional Bibliography

• Pattern recognition and machine learning, Bishop, C. M., 2006
• Python for data analysis : data wrangling with pandas, numPy, and IPhython, Mckinney, W., 2017
• Sarkar, D., Bali, R., & Sharma, T. (2018). Practical Machine Learning with Python : A Problem-Solver’s Guide to Building Real-World Intelligent Systems. [United States]: Apress. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=1667293

Authors

• KAZAKOV MAKSIM ANATOLEVICH
• GRECHIKHIN IVAN SERGEEVICH