Об этом курсе: This course is an introduction to sequence models and their applications, including an overview of sequence model architectures and how to handle inputs of variable length. • Predict future values of a time-series • Classify free form text • Address time-series and text problems with recurrent neural networks • Choose between RNNs/LSTMs and simpler models • Train and reuse word embeddings in text problems You will get hands-on practice building and optimizing your own text classification and sequence models on a variety of public datasets in the labs we’ll work on together. Prerequisites: Basic SQL, familiarity with Python and TensorFlow
Для кого этот курс: Data Engineers and programmers interested in learning how to apply machine learning in practice. Anyone interested in learning how to leverage machine learning in their enterprise.
Автор: Google Cloud
| Основные сведения | |
| Уровень | Продвинутые функции |
| Язык | English |
| Как пройти курс | Чтобы пройти курс, выполните все оцениваемые задания. |
| Оценки пользователей |
Просмотреть
Программа курса
НЕДЕЛЯ 1
Working with Sequences
In this module, you’ll learn what a sequence is, see how you can prepare sequence data for modeling, and be introduced to some classical approaches to sequence modeling and practice applying them.
14 видео, 1 материал для самостоятельного изучения
- Видео: Getting Started with Google Cloud Platform and Qwiklabs
- Reading: How to send course feedback
- Видео: Sequence data and models
- Видео: From sequences to inputs
- Видео: Modeling sequences with linear models
- Видео: Lab intro: using linear models for sequences
- Видео: Lab solution: using linear models for sequences
- Видео: Modeling sequences with DNNs
- Видео: Lab intro: using DNNs for sequences
- Видео: Lab solution: using DNNs for sequences
- Видео: Modeling sequences with CNNs
- Видео: Lab intro: using CNNs for sequences
- Видео: Lab solution: using CNNs for sequences
- Видео: The variable-length problem
Оцениваемый: Qwiklabs – Using linear models for sequences
Оцениваемый: Qwiklabs – Using DNNs for sequences
Оцениваемый: Qwiklabs – Using CNNs for sequences
Оцениваемый: Working with Sequences
Recurrent Neural Networks
In this module, we introduce recurrent neural nets, explain how they address the variable-length sequence problem, explain how our traditional optimization procedure applies to RNNs, and review the limits of what RNNs can and can’t represent.
4 видео
- Видео: How RNNs represent the past
- Видео: The limits of what RNNs can represent
- Видео: The vanishing gradient problem
Оцениваемый: Recurrent Neural Networks
Dealing with Longer Sequences
In this module we dive deeper into RNNs. We’ll talk about LSTMs, Deep RNNs, working with real world data, and more.
14 видео
- Видео: LSTMs and GRUs
- Видео: RNNs in TensorFlow
- Видео: Lab Intro: Time series prediction: end-to-end (rnn)
- Видео: Lab Solution: Time series prediction: end-to-end (rnn)
- Видео: Deep RNNs
- Видео: Lab Intro: Time series prediction: end-to-end (rnn2)
- Видео: Lab Solution: Time series prediction: end-to-end (rnn2)
- Видео: Improving our Loss Function
- Видео: Demo: Time series prediction: end-to-end (rnnN)
- Видео: Working with Real Data
- Видео: Lab Intro: Time Series Prediction - Temperature from Weather Data
- Видео: Lab Solution: Time Series Prediction - Temperature from Weather Data
- Видео: Summary
Оцениваемый: Qwiklabs – Time series prediction: end-to-end (rnn)
Оцениваемый: Qwiklabs – Time series prediction: end-to-end (rnn2)
Оцениваемый: Qwiklabs – Time Series Prediction - Temperature from Weather Data
Оцениваемый: Dealing with Longer Sequences
НЕДЕЛЯ 2
Text Classification
In this module we look at different ways of working with text and how to create your own text classification models.
8 видео
- Видео: Text Classification
- Видео: Selecting a Model
- Видео: Lab Intro: Text Classification
- Видео: Lab Solution: Text Classification
- Видео: Python vs Native TensorFlow
- Видео: Demo: Text Classification with Native TensorFlow
- Видео: Summary
Оцениваемый: Qwiklabs – Lab Solution: Text Classification
Оцениваемый: Text Classification
Reusable Embeddings
Labeled data for our classification models is expensive and precious. Here we will address how we can reuse pre-trained embeddings to make our models with TensorFlow Hub.
6 видео
- Видео: Modern methods of making word embeddings
- Видео: Introducing TensorFlow Hub
- Видео: Lab Intro: Evaluating a pre-trained embedding from TensorFlow Hub
- Видео: Lab Solution: TensorFlow Hub
- Видео: Using TensorFlow Hub within an estimator
Оцениваемый: Qwiklabs – Evaluating a pre-trained embedding from TensorFlow Hub
Оцениваемый: Reusable Embeddings
Encoder-Decoder Models
In this module, we focus on a sequence-to-sequence model called the encoder-decoder network to solve tasks, such as Machine Translation, Text Summarization and Question Answering.
10 видео
- Видео: Attention Networks
- Видео: Training Encoder-Decoder Models with TensorFlow
- Видео: Introducing Tensor2Tensor
- Видео: Lab Intro: Cloud poetry: Training custom text models on Cloud ML Engine
- Видео: Lab Solution: Cloud poetry: Training custom text models on Cloud ML Engine
- Видео: AutoML Translation
- Видео: Dialogflow
- Видео: Lab Intro: Introducing Dialogflow
- Видео: Lab Solution: Dialogflow
Оцениваемый: Qwiklabs – Evaluating a pre-trained embedding from TensorFlow HubCloud poetry: Training custom text models on Cloud ML Engine
Оцениваемый: Qwiklabs – Getting Started with Dialogflow
Оцениваемый: Encoder-Decoder Models
Summary
In this final module, we review what you have learned so far about sequence modeling for time-series and natural language data.
1 видео, 1 материал для самостоятельного изучения
- Reading: Additional Reading
Часто задаваемые вопросы
Как это работает
Trabalho
Cada curso é como um livro didático interativo, com vídeos pré-gravados, testes e projetos.
Ajuda dos seus colegas
Conecte-se com milhares de outros aprendizes, debata ideias, discuta sobre os materiais do curso e obtenha ajuda para dominar conceitos.
Certificados
Obtenha reconhecimento oficial pelo seu trabalho e compartilhe seu sucesso com amigos, colegas e empregadores.
Авторы
Google Cloud
We help millions of organizations empower their employees, serve their customers, and build what’s next for their businesses with innovative technology created in—and for—the cloud. Our products are engineered for security, reliability, and scalability, running the full stack from infrastructure to applications to devices and hardware. Our teams are dedicated to helping customers apply our technologies to create success.
Стоимость
| Приобрести курс | |
|---|---|
| Получить доступ к материалам курса | Доступен |
| Получить доступ к оцениваемым материалам курса | Доступен |
| Получить итоговую оценку | Доступен |
| Получите сертификат о прохождении курса, ссылкой на который можно делиться с другими людьми | Доступен |
Рейтинги и отзывы
Coursera делает лучшее в мире образование доступным каждому, предлагая онлайн-курсы от ведущих университетов и организаций.
© Coursera Inc., 2018 Все права защищены.
Quite a challenging course so far.