Этот курс входит в специализацию ''Специализация Advanced Machine Learning'
Introduction to Deep Learning
от партнера
Об этом курсе
4.5
Оценки: 548
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. 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.
Приобретаемые навыки
Recurrent Neural NetworkTensorflowConvolutional Neural NetworkDeep Learning
Программа курса: что вы изучите
1
Раздел
Introduction to optimization
Welcome to the "Introduction to Deep Learning" course! 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.
9 видео (всего 63 мин.), 2 материалов для самостоятельного изучения, 3 тестов
9 видео
Course intro6мин
Linear regression9мин
Linear classification10мин
Gradient descent5мин
Overfitting problem and model validation6мин
Model regularization5мин
Stochastic gradient descent5мин
Gradient descent extensions9мин
2 материала для самостоятельного изучения
Welcome!5мин
Hardware for the course10мин
2 практического упражнения
Linear models6мин
Overfitting and regularization8мин
2
Раздел
Introduction to neural networks
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.
9 видео (всего 85 мин.), 3 материалов для самостоятельного изучения, 4 тестов
9 видео
Chain rule7мин
Backpropagation9мин
Efficient MLP implementation13мин
Other matrix derivatives5мин
What is TensorFlow10мин
Our first model in TensorFlow10мин
What Deep Learning is and is not8мин
Deep learning as a language6мин
3 материала для самостоятельного изучения
Optional reading on matrix derivatives1мин
TensorFlow reading1мин
Keras reading1мин
2 практического упражнения
Multilayer perceptron10мин
Matrix derivatives20мин
3
Раздел
Deep Learning for images
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.
6 видео (всего 59 мин.), 3 тестов
6 видео
Our first CNN architecture10мин
Training tips and tricks for deep CNNs14мин
Overview of modern CNN architectures8мин
Learning new tasks with pre-trained CNNs5мин
A glimpse of other Computer Vision tasks8мин
1 практическое упражнение
Convolutions and pooling10мин
4
Раздел
Unsupervised representation learning
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.
9 видео (всего 81 мин.), 3 тестов
9 видео
Autoencoders 1015мин
Autoencoder applications9мин
Autoencoder applications: image generation, data visualization & more7мин
Natural language processing primer10мин
Word embeddings13мин
Generative models 1017мин
Generative Adversarial Networks10мин
Applications of adversarial approach11мин
1 практическое упражнение
Word embeddings8мин
4.5
22%
83%
Лучшие рецензии
автор: YG•Jan 28th 2018
This is a very hands on Deep Learning class. Like the design of programming assignments a lot. It's very instructive as well as challenging! Great course. I would recommend it!
автор: AS•Mar 26th 2018
Great course! The faculty does an excellent job in explaining some difficult to understand concepts. The discussion forum is very active and the course community is helpful.
Преподавателя
Evgeny Sokolov
Senior LecturerHSE Faculty of Computer Science
Andrei Zimovnov
Senior LecturerHSE Faculty of Computer Science
Alexander Panin
LecturerHSE Faculty of Computer Science
Ekaterina Lobacheva
Senior LecturerHSE Faculty of Computer Science
Nikita Kazeev
ResearcherHSE Faculty of Computer Science
О National Research University Higher School of Economics
National Research University - Higher School of Economics (HSE) is one of the top research universities in Russia. Established in 1992 to promote new research and teaching in economics and related disciplines, it now offers programs at all levels of university education across an extraordinary range of fields of study including business, sociology, cultural studies, philosophy, political science, international relations, law, Asian studies, media and communications, IT, mathematics, engineering, and more.
Learn more on www.hse.ru
О специализации ''Advanced Machine Learning'
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.
Часто задаваемые вопросы
When will I have access to the lectures and assignments?
Once you enroll for a Certificate, you’ll have access to all videos, quizzes, and programming assignments (if applicable). Peer review assignments can only be submitted and reviewed once your session has begun. If you choose to explore the course without purchasing, you may not be able to access certain assignments.
What will I get if I subscribe to this Specialization?
When you enroll in the course, you get access to all of the courses in the Specialization, and you earn a certificate when you complete the work. Your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile. If you only want to read and view the course content, you can audit the course for free.
What is the refund policy?
Is financial aid available?
Остались вопросы? Посетите Центр поддержки учащихся.
Coursera делает лучшее в мире образование доступным каждому, предлагая онлайн-курсы от ведущих университетов и организаций.
© Coursera Inc., 2018 Все права защищены.
