Coursera
Explorar
  • Explorar
  • Buscar
  • For Enterprise
  • Inicia Sesión
  • Regístrarse

Introduction to Deep Learning

Un vistazoProgramaPreguntas FrecuentesCreadoresTarifaCalificaciones y revisiones

InicioCiencia de DatosAprendizaje Automático

Introduction to Deep Learning

National Research University Higher School of Economics

Acerca de este curso: 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.

Para quién es esta clase: Developers, analysts and researchers who are faced with tasks involving complex structure understanding such as image, sound and text analysis.


Creada por:  National Research University Higher School of Economics
National Research University Higher School of Economics

  • Evgeny Sokolov

    Enseñado por:  Evgeny Sokolov, Senior Lecturer

    HSE Faculty of Computer Science

  • Andrei Zimovnov

    Enseñado por:  Andrei Zimovnov, Senior Lecturer

    HSE Faculty of Computer Science

  • Alexander Panin

    Enseñado por:  Alexander Panin, Lecturer

    HSE Faculty of Computer Science

  • Ekaterina Lobacheva

    Enseñado por:  Ekaterina Lobacheva, Senior Lecturer

    HSE Faculty of Computer Science

  • Nikita Kazeev

    Enseñado por:  Nikita Kazeev, Researcher

    HSE Faculty of Computer Science
Información básica
Curso 1 de 7 en Advanced Machine Learning Specialization
NivelAdvanced
Compromiso6 weeks of study, 6-10 hours/week
Idioma
English
Cómo aprobarAprueba todas las tareas calificadas para completar el curso.
Calificaciones del usuario
4.4 estrellas
Calificación promedio del usuario 4.4Ve los que los estudiantes dijeron
Programa
SEMANA 1
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.
7 videos, 1 reading
  1. Reading: Welcome!
  2. Vídeo: Linear regression
  3. Vídeo: Linear classification
  4. Vídeo: Gradient descent
  5. Vídeo: Overfitting problem and model validation
  6. Vídeo: Model regularization
  7. Vídeo: Stochastic gradient descent
  8. Vídeo: Gradient descent extensions
  9. Notebook: Linear models and optimization
Calificado: Linear models
Calificado: Overfitting and regularization
Calificado: Linear models and optimization
SEMANA 2
Introduction to neural networks
This module is an introduction to the concept of a deep neural network. You'll begin with the linear model in numpy and finish with writing your very first deep network.
8 videos, 1 practice quiz
  1. Vídeo: Multilayer perceptron
  2. Vídeo: Training a neural network
  3. Vídeo: Backpropagation primer
  4. Practice Quiz: Multilayer perceptron
  5. Notebook: Tensorflow_task.ipynb
  6. Vídeo: Going deeper with Tensorflow
  7. Ungraded Programming: MSE in TensorFlow
  8. Vídeo: Gradients & optimization in Tensorflow
  9. Notebook: my1stNN boilerplate
  10. Notebook: Keras-task.ipynb
  11. Vídeo: Keras introduction
  12. Vídeo: What Deep Learning is and is not
  13. Vídeo: Deep learning as a language
  14. Notebook: NumpyNN (honor).ipynb
Calificado: Logistic regression in TensorFlow
Calificado: my1stNN
Calificado: my1stNN - Keras this time
Calificado: Your very own neural network
SEMANA 3
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 videos
  1. Vídeo: Motivation for convolutional layers
  2. Vídeo: Our first CNN architecture
  3. Vídeo: Training tips and tricks for deep CNNs
  4. Vídeo: Overview of modern CNN architectures
  5. Notebook: Your first CNN on CIFAR-10
  6. Vídeo: Learning new tasks with pre-trained CNNs
  7. Vídeo: A glimpse of other Computer Vision tasks
  8. Notebook: Fine-tuning InceptionV3 for flowers classification
Calificado: Convolutions and pooling
Calificado: Your first CNN on CIFAR-10
Calificado: Fine-tuning InceptionV3 for flowers classification
SEMANA 4
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 videos
  1. Vídeo: Unsupervised learning: what it is and why bother
  2. Vídeo: Autoencoders 101
  3. Vídeo: Autoencoder applications
  4. Vídeo: Autoencoder applications: image generation, data visualization & more
  5. Notebook: Autoencoders.ipynb
  6. Vídeo: Natural language processing primer
  7. Vídeo: Word embeddings
  8. Vídeo: Generative models 101
  9. Vídeo: Generative Adversarial Networks
  10. Vídeo: Applications of adversarial approach
  11. Notebook: Generative Adversarial Networks
Calificado: Simple autoencoder
Calificado: Word embeddings
Calificado: Generative adversarial networks
SEMANA 5
Deep learning for sequences
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.
6 videos
  1. Vídeo: Motivation for recurrent layers
  2. Vídeo: Simple RNN and Backpropagation
  3. Notebook: Generating names with RNNs
  4. Vídeo: The training of RNNs is not that easy
  5. Vídeo: Dealing with vanishing and exploding gradients
  6. Vídeo: Modern RNNs: LSTM and GRU
  7. Notebook: More RNNs in Keras
  8. Vídeo: Practical use cases for RNNs
Calificado: RNN and Backpropagation
Calificado: Generating names with RNNs
Calificado: Modern RNNs
Calificado: How to use RNNs
SEMANA 6
Final Project
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!
3 items
  1. Notebook: Image Captioning Final Project
Calificado: Image Captioning Final Project
Calificado: Image Captioning Final Project

Preguntas Frecuentes
Cómo funciona
Coursework
Coursework

Each course is like an interactive textbook, featuring pre-recorded videos, quizzes and projects.

Help from Your Peers
Help from Your Peers

Connect with thousands of other learners and debate ideas, discuss course material, and get help mastering concepts.

Certificates
Certificates

Earn official recognition for your work, and share your success with friends, colleagues, and employers.

Creadores
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
Tarifa
Comprar curso
Accede a los materiales del curso

Disponible

Accede a los materiales con calificación

Disponible

Recibe una calificación final

Disponible

Obtén un Certificado de curso para compartir

Disponible

Calificaciones y revisiones
Calificado 4.4 de 5 267 calificaciones

KD

I didn't watch the videos as I wanted to try my current know-how on the assignments directly, but I can only recommend doing them, as they will provide you with great guidelines on implementing and training different types of neural networks. Even for a fairly experienced data scientist, the assignments were compelling enough.

Ahmed Nabil

It is great and rich contents i studied machine learning a lot and this one is very useful and beneficial to me thanks a lot.

AS

It is not an easy course, but the course projects are very nice. I really liked the RNN and CNN parts of this course very well explained and had some rigour to it.

My only complaint about the course is that it is not self contained. You will have to read up a lot more and refer to other sources on the internet to get a firm grasp of what is being taught and then go ahead to tackle the exercises.

RS

Interesting content but some videos do not explain the topics well enough and some extra study is needed.



También te podría gustar
deeplearning.ai
Structuring Machine Learning Projects
1 course
deeplearning.ai
Structuring Machine Learning Projects
Ver curso
deeplearning.ai
Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization
1 course
deeplearning.ai
Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization
Ver curso
deeplearning.ai
Convolutional Neural Networks
1 course
deeplearning.ai
Convolutional Neural Networks
Ver curso
deeplearning.ai
Sequence Models
1 course
deeplearning.ai
Sequence Models
Ver curso
deeplearning.ai
Neural Networks and Deep Learning
1 course
deeplearning.ai
Neural Networks and Deep Learning
Ver curso
Coursera
Coursera brinda acceso universal a la mejor educación del mundo, al asociarse con las mejores universidades y organizaciones, para ofrecer cursos en línea.
© 2018 Coursera Inc. Todos los derechos reservados.
Descargar en la App StoreConsíguelo en Google Play
  • Coursera
  • Acerca de
  • Liderazgo
  • Empleo
  • Catálogo
  • Certificados
  • Grados
  • Para negocios
  • For Government
  • Comunidad
  • instituciones
  • Mentores
  • Traductores
  • Desarrolladores
  • Probador beta
  • Conectar
  • Blog
  • Facebook
  • LinkedIn
  • Twitter
  • Google+
  • Blog de Tecnología
  • Más
  • Términos
  • Privacidad
  • Ayuda
  • Accesibilidad
  • Prensa
  • Contacto
  • Directorio
  • Afiliados