Introduction to Deep Learning

The course starts with a recap of linear models and discussion of stochastic optimization methods that are crucial for training deep neural networks

  • The course is related to the online specialization ''Deep Learning"
  • Flexible Terms
  • 6 weeks (3 credits)
  • Time to completion: 35 hours
  • Online course
  • Certificate

About the Course

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

Course Objectives


01

Get basic understanding of modern neural networks


02

Learn how to apply neural networks to computer vision


03

Learn how to apply neural networks to natural language understanding

Learning Outcomes

1. Recurrent Neural Network

2. Tensorflow

3. Convolutional Neural Network

4. Deep Learning

Course Syllabus

Week 1. Introduction to optimization

Week 2. Introduction to neural networks

Week 3. Deep Learning for images

Week 4. Unsupervised representation learning

Week 5. Deep learning for sequences

Week 6. Final Project




Teachers

Соколов Евгений Андреевич

Центр непрерывного образования: Научный руководитель

Зимовнов Андрей Вадимович

Базовая кафедра Яндекс: Старший преподаватель

Лобачева Екатерина Максимовна

Центр глубинного обучения и байесовских методов: Научный сотрудник

Alexander Panin

HSE Faculty of Computer Science: Lecturer

Nikita Kazeev

HSE Faculty of Computer Science: Researcher

Prerequisites

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. 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

Graduation Document

Earn a Certificate upon completion

 

 

Learning Activities


Lectures

Online


Low-Stakes Assignments

Tests


High-Stakes Assignments

Final project


Cost and Conditions


16 000 ₽

Full access to the learning materials + Graduation document

More: публичная оферта