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
Этот курс входит в специализацию ''Специализация Advanced Machine Learning with TensorFlow on Google Cloud Platform'
Sequence Models for Time Series and Natural Language Processing
от партнера
Программа курса: что вы изучите
Неделя
14 ч. на завершение
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 ((всего 41 мин.)), 1 материал для самостоятельного изучения, 4 тестов
14 видео
Getting Started with Google Cloud Platform and Qwiklabs3мин
Sequence data and models5мин
From sequences to inputs2мин
Modeling sequences with linear models2мин
Lab intro: using linear models for sequences20
Lab solution: using linear models for sequences7мин
Modeling sequences with DNNs2мин
Lab intro: using DNNs for sequences19
Lab solution: using DNNs for sequences2мин
Modeling sequences with CNNs3мин
Lab intro: using CNNs for sequences19
Lab solution: using CNNs for sequences3мин
The variable-length problem4мин
1 материал для самостоятельного изучения
How to send course feedback10мин
1 практическое упражнение
Working with Sequences
15 минуты на завершение
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 ((всего 15 мин.)), 1 тест
4 видео
How RNNs represent the past4мин
The limits of what RNNs can represent5мин
The vanishing gradient problem1мин
1 практическое упражнение
Recurrent Neural Networks
4 ч. на завершение
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 ((всего 62 мин.)), 4 тестов
14 видео
Introduction2мин
LSTMs and GRUs6мин
RNNs in TensorFlow2мин
Lab Intro: Time series prediction: end-to-end (rnn)45
Lab Solution: Time series prediction: end-to-end (rnn)10мин
Deep RNNs1мин
Lab Intro: Time series prediction: end-to-end (rnn2)26
Lab Solution: Time series prediction: end-to-end (rnn2)6мин
Improving our Loss Function2мин
Demo: Time series prediction: end-to-end (rnnN)3мин
Working with Real Data10мин
Lab Intro: Time Series Prediction - Temperature from Weather Data1мин
Lab Solution: Time Series Prediction - Temperature from Weather Data11мин
Summary1мин
1 практическое упражнение
Dealing with Longer Sequences
Неделя
22 ч. на завершение
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 ((всего 35 мин.)), 2 тестов
8 видео
Text Classification6мин
Selecting a Model2мин
Lab Intro: Text Classification47
Lab Solution: Text Classification11мин
Python vs Native TensorFlow4мин
Demo: Text Classification with Native TensorFlow7мин
Summary1мин
1 практическое упражнение
Text Classification
1 ч. на завершение
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 ((всего 28 мин.)), 2 тестов
6 видео
Modern methods of making word embeddings8мин
Introducing TensorFlow Hub1мин
Lab Intro: Evaluating a pre-trained embedding from TensorFlow Hub24
Lab Solution: TensorFlow Hub9мин
Using TensorFlow Hub within an estimator1мин
1 практическое упражнение
Reusable Embeddings
3 ч. на завершение
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 ((всего 84 мин.)), 3 тестов
10 видео
Attention Networks4мин
Training Encoder-Decoder Models with TensorFlow6мин
Introducing Tensor2Tensor11мин
Lab Intro: Cloud poetry: Training custom text models on Cloud ML Engine1мин
Lab Solution: Cloud poetry: Training custom text models on Cloud ML Engine25мин
AutoML Translation4мин
Dialogflow6мин
Lab Intro: Introducing Dialogflow54
Lab Solution: Dialogflow13мин
1 практическое упражнение
Encoder-Decoder Models
14 минуты на завершение
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 ((всего 4 мин.)), 1 материал для самостоятельного изучения
1 видео
Summary3мин
1 материал для самостоятельного изучения
Additional Reading10мин
4.5
Рецензии: 20Лучшие отзывы о курсе Sequence Models for Time Series and Natural Language Processing
Excellent course for those who know RNN. Knowledge is refreshed and techniques are consolidated. More details about Google ecosystem is introduced.
Very good.The explanation of the RNN was very good but the tensor2tensor was very hard.
О 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.
О специализации ''Advanced Machine Learning with TensorFlow on Google Cloud Platform'
This 5-course specialization focuses on advanced machine learning topics using Google Cloud Platform where you will get hands-on experience optimizing, deploying, and scaling production ML models of various types in hands-on labs. This specialization picks up where “Machine Learning on GCP” left off and teaches you how to build scalable, accurate, and production-ready models for structured data, image data, time-series, and natural language text. It ends with a course on building recommendation systems. Topics introduced in earlier courses are referenced in later courses, so it is recommended that you take the courses in exactly this order.
Часто задаваемые вопросы
Можно ли ознакомиться с курсом до регистрации?
Да, до регистрации можно просмотреть первое видео и программу курса. Чтобы получить полный доступ к материалам курса, необходимо оплатить его.
Когда я получу доступ к лекциям и заданиям?
Регистрируясь на курс до начала сессии, вы получаете доступ ко всем видеолекциям и материалам для самостоятельного изучения. Задания можно отправлять после начала сессии.
Что я получу, зарегистрировавшись на курс?
После регистрации на курс и начала сессии вы получаете доступ ко всем видео и другим ресурсам курса, включая материалы для самостоятельного изучения и форумы обсуждений. Вы сможете выполнять тренировочные, а также сдавать обязательные оцениваемые задания и получить сертификат о прохождении курса.
Когда я получу сертификат о прохождении курса?
Если вы успешного пройдете курс, на странице ваших достижений появится электронный сертификат, который можно распечатать или прикрепить к профилю LinkedIn.
Почему я не могу прослушать этот курс?
Это один из немногих курсов на Coursera, которые предоставляются только на платной основе.
Какие правила возврата средств?
Можно ли получить финансовую помощь?
Остались вопросы? Посетите Центр поддержки учащихся.
Coursera provides universal access to the world’s best education,
partnering with top universities and organizations to offer courses online.
© Coursera Inc., 2019 Все права защищены.
