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
This course is part of the Advanced Machine Learning with TensorFlow on Google Cloud Platform Specialization
Sequence Models for Time Series and Natural Language Processing
Offered By
Syllabus - What you will learn from this course
Week
14 hours to complete
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 videos (Total 41 min), 1 reading, 4 quizzes
14 videos
Getting Started with Google Cloud Platform and Qwiklabs3m
Sequence data and models5m
From sequences to inputs2m
Modeling sequences with linear models2m
Lab intro: using linear models for sequences20s
Lab solution: using linear models for sequences7m
Modeling sequences with DNNs2m
Lab intro: using DNNs for sequences19s
Lab solution: using DNNs for sequences2m
Modeling sequences with CNNs3m
Lab intro: using CNNs for sequences19s
Lab solution: using CNNs for sequences3m
The variable-length problem4m
1 reading
How to send course feedback10m
1 practice exercise
Working with Sequences
15 minutes to complete
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 videos (Total 15 min), 1 quiz
4 videos
How RNNs represent the past4m
The limits of what RNNs can represent5m
The vanishing gradient problem1m
1 practice exercise
Recurrent Neural Networks
4 hours to complete
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 videos (Total 62 min), 4 quizzes
14 videos
LSTMs and GRUs6m
RNNs in TensorFlow2m
Lab Intro: Time series prediction: end-to-end (rnn)45s
Lab Solution: Time series prediction: end-to-end (rnn)10m
Deep RNNs1m
Lab Intro: Time series prediction: end-to-end (rnn2)26s
Lab Solution: Time series prediction: end-to-end (rnn2)6m
Improving our Loss Function2m
Demo: Time series prediction: end-to-end (rnnN)3m
Working with Real Data10m
Lab Intro: Time Series Prediction - Temperature from Weather Data1m
Lab Solution: Time Series Prediction - Temperature from Weather Data11m
Summary1m
1 practice exercise
Dealing with Longer Sequences
Week
22 hours to complete
Text Classification
In this module we look at different ways of working with text and how to create your own text classification models.
8 videos (Total 35 min), 2 quizzes
8 videos
Text Classification6m
Selecting a Model2m
Lab Intro: Text Classification47s
Lab Solution: Text Classification11m
Python vs Native TensorFlow4m
Demo: Text Classification with Native TensorFlow7m
Summary1m
1 practice exercise
Text Classification
1 hour to complete
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 videos (Total 28 min), 2 quizzes
6 videos
Modern methods of making word embeddings8m
Introducing TensorFlow Hub1m
Lab Intro: Evaluating a pre-trained embedding from TensorFlow Hub24s
Lab Solution: TensorFlow Hub9m
Using TensorFlow Hub within an estimator1m
1 practice exercise
Reusable Embeddings
3 hours to complete
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 videos (Total 84 min), 3 quizzes
10 videos
Attention Networks4m
Training Encoder-Decoder Models with TensorFlow6m
Introducing Tensor2Tensor11m
Lab Intro: Cloud poetry: Training custom text models on Cloud AI Platform1m
Lab Solution: Cloud poetry: Training custom text models on Cloud AI Platform25m
AutoML Translation4m
Dialogflow6m
Lab Intro: Introducing Dialogflow54s
Lab Solution: Dialogflow13m
1 practice exercise
Encoder-Decoder Models
14 minutes to complete
Summary
In this final module, we review what you have learned so far about sequence modeling for time-series and natural language data.
1 video (Total 4 min), 1 reading
1 video
Summary3m
1 reading
Additional Reading10m
4.5
27 Reviews50%
started a new career after completing these courses
67%
got a tangible career benefit from this course
Top reviews from Sequence Models for Time Series and Natural Language Processing
Great way to practically learn a lot of stuff. Sometimes, a lot of it starts to go over head. But, it is completely worth the learning curve! Definitely recommend it!
Excellent course for those who know RNN. Knowledge is refreshed and techniques are consolidated. More details about Google ecosystem is introduced.
About 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.
About the Advanced Machine Learning with TensorFlow on Google Cloud Platform Specialization
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.
Frequently Asked Questions
Can I preview a course before enrolling?
Yes, you can preview the first video and view the syllabus before you enroll. You must purchase the course to access content not included in the preview.
When will I have access to the lectures and assignments?
If you decide to enroll in the course before the session start date, you will have access to all of the lecture videos and readings for the course. You’ll be able to submit assignments once the session starts.
What will I get when I enroll?
Once you enroll and your session begins, you will have access to all videos and other resources, including reading items and the course discussion forum. You’ll be able to view and submit practice assessments, and complete required graded assignments to earn a grade and a Course Certificate.
When will I receive my Course Certificate?
If you complete the course successfully, your electronic Course Certificate will be added to your Accomplishments page - from there, you can print your Course Certificate or add it to your LinkedIn profile.
Why can’t I audit this course?
This course is one of a few offered on Coursera that are currently available only to learners who have paid or received financial aid, when available.
What is the refund policy?
Is financial aid available?
More questions? Visit the Learner Help Center.