***NEW! Specialization Completion Challenge, receive Qwiklabs credits valued up to $150! See below for details.***
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
SPECIALIZATION COMPLETION CHALLENGE
As if learning new skills wasn’t enough of an incentive, we're excited to announce a special completion challenge for 'Advanced Machine Learning with TensorFlow on GCP’ specialization.
Here’s how it works: Our completion challenge runs through 11:59pm PT May 5, 2019. Complete any course in this Specialization including this one, anytime in this period and we'll send you 30 Qwiklabs credits for each course completed (upto $150 value given there are 5 courses in the specialization).
You can use these credits to take additional labs and earn badges, which you can then add to your resume and social profiles.
Your challenge awaits – begin learning on Coursera today!
Ce cours fait partie de la Spécialisation Advanced Machine Learning with TensorFlow on Google Cloud Platform
Sequence Models for Time Series and Natural Language Processing
proposé par
Programme du cours : ce que vous apprendrez dans ce cours
Semaine
14 heures pour terminer
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 vidéos (Total 41 min), 1 lecture, 4 quiz
14 vidéos
Course Introduction1 min
Getting Started with Google Cloud Platform and Qwiklabs3 min
Sequence data and models5 min
From sequences to inputs2 min
Modeling sequences with linear models2 min
Lab intro: using linear models for sequences20s
Lab solution: using linear models for sequences7 min
Modeling sequences with DNNs2 min
Lab intro: using DNNs for sequences19s
Lab solution: using DNNs for sequences2 min
Modeling sequences with CNNs3 min
Lab intro: using CNNs for sequences19s
Lab solution: using CNNs for sequences3 min
The variable-length problem4 min
1 lecture
How to send course feedback10 min
1 exercice pour s'entraîner
Working with Sequences
15 minutes pour terminer
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 vidéos (Total 15 min), 1 quiz
4 vidéos
How RNNs represent the past4 min
The limits of what RNNs can represent5 min
The vanishing gradient problem1 min
1 exercice pour s'entraîner
Recurrent Neural Networks
4 heures pour terminer
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 vidéos (Total 62 min), 4 quiz
14 vidéos
Introduction2 min
LSTMs and GRUs6 min
RNNs in TensorFlow2 min
Lab Intro: Time series prediction: end-to-end (rnn)45s
Lab Solution: Time series prediction: end-to-end (rnn)10 min
Deep RNNs1 min
Lab Intro: Time series prediction: end-to-end (rnn2)26s
Lab Solution: Time series prediction: end-to-end (rnn2)6 min
Improving our Loss Function2 min
Demo: Time series prediction: end-to-end (rnnN)3 min
Working with Real Data10 min
Lab Intro: Time Series Prediction - Temperature from Weather Data1 min
Lab Solution: Time Series Prediction - Temperature from Weather Data11 min
Summary1 min
1 exercice pour s'entraîner
Dealing with Longer Sequences
Semaine
22 heures pour terminer
Text Classification
In this module we look at different ways of working with text and how to create your own text classification models.
8 vidéos (Total 35 min), 2 quiz
8 vidéos
Working with Text1 min
Text Classification6 min
Selecting a Model2 min
Lab Intro: Text Classification47s
Lab Solution: Text Classification11 min
Python vs Native TensorFlow4 min
Demo: Text Classification with Native TensorFlow7 min
Summary1 min
1 exercice pour s'entraîner
Text Classification
1 heure pour terminer
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 vidéos (Total 28 min), 2 quiz
6 vidéos
Modern methods of making word embeddings8 min
Introducing TensorFlow Hub1 min
Lab Intro: Evaluating a pre-trained embedding from TensorFlow Hub24s
Lab Solution: TensorFlow Hub9 min
Using TensorFlow Hub within an estimator1 min
1 exercice pour s'entraîner
Reusable Embeddings
3 heures pour terminer
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 vidéos (Total 84 min), 3 quiz
10 vidéos
Attention Networks4 min
Training Encoder-Decoder Models with TensorFlow6 min
Introducing Tensor2Tensor11 min
Lab Intro: Cloud poetry: Training custom text models on Cloud ML Engine1 min
Lab Solution: Cloud poetry: Training custom text models on Cloud ML Engine25 min
AutoML Translation4 min
Dialogflow6 min
Lab Intro: Introducing Dialogflow54s
Lab Solution: Dialogflow13 min
1 exercice pour s'entraîner
Encoder-Decoder Models
14 minutes pour terminer
Summary
In this final module, we review what you have learned so far about sequence modeling for time-series and natural language data.
1 vidéo (Total 4 min), 1 lecture
1 vidéo
Summary3 min
1 lecture
Additional Reading10 min
4.5
15 avisMeilleurs avis
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.
À propos de 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.
À propos de la Spécialisation Advanced Machine Learning with TensorFlow on Google Cloud Platform
>>>Look for details below for COMPLETION CHALLENGE, receive up to $150 in Qwiklabs credits<<<
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.
COMPLETION CHALLENGE
For every course you complete before 11:59pm PT May 5, 2019; we will send you 30 Qwiklabs credits (upto $150 USD value)!
Foire Aux Questions
Puis-je prévisualiser un cours avant de m'inscrire ?
Oui, vous pouvez prévisualiser la première vidéo et consulter le programme du cours avant de vous inscrire. Vous devez acheter le cours pour accéder au contenu non inclus dans la prévisualisation.
Quand aurai-je accès aux vidéos de cours et aux devoirs ?
Si vous décidez de vous inscrire au cours avant la date de début de session, vous aurez accès à toutes les vidéos et lectures du cours. Vous pourrez soumettre des devoirs à partir du début de la session.
À quoi ai-je droit si je m'inscris ?
Une fois que vous êtes inscrit(e) et que votre session commence, vous avez accès à toutes les vidéos et aux autres ressources, y compris les éléments à lire et le forum de discussion du cours. Vous pouvez afficher et soumettre des devoirs pour vous exercer, et terminer les devoirs notés requis pour obtenir une note et un Certificat de Cours.
Quand recevrai-je mon Certificat de Cours ?
Si vous réussissez le cours, votre Certificat de Cours électronique sera ajouté à votre page Accomplissements. À partir de cette page, vous pouvez imprimer votre Certificat de Cours ou l'ajouter à votre profil LinkedIn.
Pourquoi ne puis-je pas assister à ce cours en auditeur libre ?
Ce cours fait partie du nombre restreint de cours proposés par Coursera actuellement disponibles uniquement aux étudiants ayant payé les frais du cours ou bénéficié de l'Aide Financière, lorsqu'elle est disponible.
Quelle est la politique de remboursement ?
Une aide financière est-elle possible ?
D'autres questions ? Visitez le Centre d'Aide pour les Etudiants.
Coursera propose un accès universel à la meilleure formation au monde,
en partenariat avec des universités et des organisations du plus haut niveau, pour proposer des cours en ligne.
© 2019 Coursera Inc. Tous droits réservés.
