Introduction to Machine Learning

2020/2021

Academic Year

RUS

Instruction in Russian

3

ECTS credits

Delivered at:

Практико-ориентированные магистерские программы факультета экономических наук

Course type:

Elective course

When:

2 year, 2 module

Instructor

Kurochkin, Sergey V.

Программа дисциплины

Аннотация

This specialization gives an introduction to deep learning, reinforcement learning, natural language understanding, computer vision and Bayesian methods. Top Kaggle machine learning practitioners and CERN scientists will share their experience of solving real-world problems and help you to fill the gaps between theory and practice. Upon completion of 7 courses you will be able to apply modern machine learning methods in enterprise and understand the caveats of real-world data and settings.

Цель освоения дисциплины

• The goal of this course is to give learners basic understanding of modern neural networks and their applications in computer vision and natural language understanding.

Планируемые результаты обучения

• We'll consider the reinforcement learning formalisms in a more rigorous, mathematical way. You'll learn how to effectively compute the return your agent gets for a particular action - and how to pick best actions based on that return.
• We'll find out how to apply last week's ideas to the real world problems: ones where you don't have a perfect model of your environment.
• We'll learn to scale things even farther up by training agents based on neural networks.
• You'll learn how to build better exploration strategies with a focus on contextual bandit setup

Содержание учебной дисциплины

• Intro: why should i care?
  In this module we gonna define and "taste" what reinforcement learning is about. We'll also learn one simple algorithm that can solve reinforcement learning problems with embarrassing efficiency.
• At the heart of RL: Dynamic Programming
  This week we'll consider the reinforcement learning formalisms in a more rigorous, mathematical way. You'll learn how to effectively compute the return your agent gets for a particular action - and how to pick best actions based on that return.
• Model-free methods
  This week we'll find out how to apply last week's ideas to the real world problems: ones where you don't have a perfect model of your environment.
• Approximate Value Based Methods
  This week we'll learn to scale things even farther up by training agents based on neural networks.
• Policy-based methods
  We spent 3 previous modules working on the value-based methods: learning state values, action values and whatnot. Now's the time to see an alternative approach that doesn't require you to predict all future rewards to learn something.
• Exploration
  In this final week you'll learn how to build better exploration strategies with a focus on contextual bandit setup. In honor track, you'll also learn how to apply reinforcement learning to train structured deep learning models.

Элементы контроля

• Tests
• Tasks

Промежуточная аттестация

• Промежуточная аттестация (2 модуль)
  0.5 * Tasks + 0.5 * Tests

Список литературы

Рекомендуемая основная литература

• Fabozzi, F. J. (2002). The Handbook of Financial Instruments. Hoboken, N.J.: Wiley. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=81949
• Анализ данных на компьютере, Тюрин, Ю. Н., 2003

Рекомендуемая дополнительная литература

• Microsoft SQL Server 2005 Analysis Services. OLAP и многомерный анализ данных, Бергер, А., 2007