• A
  • A
  • A
  • АБB
  • АБB
  • АБB
  • А
  • А
  • А
  • А
  • А
Обычная версия сайта
Магистратура 2019/2020

Введение в глубинное обучение

Лучший по критерию «Полезность курса для Вашей будущей карьеры»
Лучший по критерию «Полезность курса для расширения кругозора и разностороннего развития»
Лучший по критерию «Новизна полученных знаний»
Статус: Курс по выбору (Суперкомпьютерное моделирование в науке и инженерии)
Направление: 01.04.04. Прикладная математика
Когда читается: 2-й курс, 3 модуль
Формат изучения: с онлайн-курсом
Прогр. обучения: Суперкомпьютерное моделирование в науке и инженерии
Язык: английский
Кредиты: 3
Контактные часы: 4

Course Syllabus

Abstract

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. The course starts with a recap of linear models and discussion of stochastic optimization methods that are crucial for training deep neural networks. Learners will study all popular building blocks of neural networks including fully connected layers, convolutional and recurrent layers. Learners will use these building blocks to define complex modern architectures in TensorFlow and Keras frameworks. In the course project learner will implement deep neural network for the task of image captioning which solves the problem of giving a text description for an input image. The prerequisites for this course are: 1) Basic knowledge of Python. 2) Basic linear algebra and probability. Please note that this is an advanced course and we assume basic knowledge of machine learning. https://www.coursera.org/learn/intro-to-deep-learning
Learning Objectives

Learning Objectives

  • You should understand: 1) Linear regression: mean squared error, analytical solution. 2) Logistic regression: model, cross-entropy loss, class probability estimation. 3) Gradient descent for linear models. Derivatives of MSE and cross-entropy loss functions. 4) The problem of overfitting. 5) Regularization for linear models.
Expected Learning Outcomes

Expected Learning Outcomes

  • Understand: Linear regression: mean squared error, analytical solution
  • Understand:Logistic regression: model, cross-entropy loss, class probability estimation.
  • Understand: Gradient descent for linear models. Derivatives of MSE and cross-entropy loss functions.
  • Understand: The problem of overfitting.
  • Understand: Regularization for linear models.
  • Chatterbot, Tensorflow, Deep Learning, Natural Language Processing
Course Contents

Course Contents

  • Неделя 1
    In the first week you'll learn about linear models and stochatic optimization methods. Linear models are basic building blocks for many deep architectures, and stochastic optimization is used to learn every model that we'll discuss in our course.
  • Неделя 2
    This module is an introduction to the concept of a deep neural network. You'll begin with the linear model and finish with writing your very first deep network.
  • Неделя 3
    In this week you will learn about building blocks of deep learning for image input. You will learn how to build Convolutional Neural Network (CNN) architectures with these blocks and how to quickly solve a new task using so-called pre-trained models.
  • Неделя 4
    This week we're gonna dive into unsupervised parts of deep learning. You'll learn how to generate, morph and search images with deep learning.
  • Неделя 5
    In this week you will learn how to use deep learning for sequences such as texts, video, audio, etc. You will learn about several Recurrent Neural Network (RNN) architectures and how to apply them for different tasks with sequential input/output.
  • Неделя 6
    In this week you will apply all your knowledge about neural networks for images and texts for the final project. You will solve the task of generating descriptions for real world images!
Assessment Elements

Assessment Elements

  • non-blocking Оценивание проводится в форме собеседования после предъявления студентом результатов тестирования.
  • non-blocking результаты прохождения курса на coursera.org
  • non-blocking Контрольно-измерительные материалы
Interim Assessment

Interim Assessment

  • Interim assessment (3 module)
    0.5 * Оценивание проводится в форме собеседования после предъявления студентом результатов тестирования. + 0.5 * результаты прохождения курса на coursera.org
Bibliography

Bibliography

Recommended Core Bibliography

  • Deep learning, Goodfellow, I., 2016

Recommended Additional Bibliography

  • Linear algebra : concepts and methods, Anthony, M., 2012