Sequences, Time Series and Prediction
Keep adding new skills with 10,000+ programs for $239 (usually $399). Save now.
Sequences, Time Series and Prediction
This course is part of DeepLearning.AI TensorFlow Developer Professional Certificate
Instructor: Laurence Moroney
151,558 already enrolled
5,162 reviews
Recommended experience
5,162 reviews
Recommended experience
What you'll learn
Solve time series and forecasting problems in TensorFlow
Prepare data for time series learning using best practices
Explore how RNNs and ConvNets can be used for predictions
Build a sunspot prediction model using real-world data
Skills you'll gain
Tools you'll learn
Details to know
4 assignments
See how employees at top companies are mastering in-demand skills
Build your Machine Learning expertise
- Learn new concepts from industry experts
- Gain a foundational understanding of a subject or tool
- Develop job-relevant skills with hands-on projects
- Earn a shareable career certificate from DeepLearning.AI
There are 4 modules in this course
If you are a software developer who wants to build scalable AI-powered algorithms, you need to understand how to use the tools to build them. This Specialization will teach you best practices for using TensorFlow, a popular open-source framework for machine learning.
In this fourth course, you will learn how to build time series models in TensorFlow. You’ll first implement best practices to prepare time series data. You’ll also explore how RNNs and 1D ConvNets can be used for prediction. Finally, you’ll apply everything you’ve learned throughout the Specialization to build a sunspot prediction model using real-world data! The Machine Learning course and Deep Learning Specialization from Andrew Ng teach the most important and foundational principles of Machine Learning and Deep Learning. This new DeepLearning.AI TensorFlow Developer Specialization teaches you how to use TensorFlow to implement those principles so that you can start building and applying scalable models to real-world problems. To develop a deeper understanding of how neural networks work, we recommend that you take the Deep Learning Specialization.
Hi Learners and welcome to this course on sequences and prediction! In this course we'll take a look at some of the unique considerations involved when handling sequential time series data -- where values change over time, like the temperature on a particular day, or the number of visitors to your web site. We'll discuss various methodologies for predicting future values in these time series, building on what you've learned in previous courses!
What's included
10 videos7 readings1 assignment1 programming assignment2 ungraded labs
10 videos•Total 32 minutes
- Introduction: A conversation with Andrew Ng•3 minutes
- Time series examples•4 minutes
- Machine learning applied to time series•2 minutes
- Common patterns in time series•5 minutes
- Introduction to time series•4 minutes
- Train, validation and test sets•3 minutes
- Metrics for evaluating performance•2 minutes
- Moving average and differencing•3 minutes
- Trailing versus centered windows•1 minute
- Forecasting•4 minutes
7 readings•Total 18 minutes
- Welcome to the course!•1 minute
- About the notebooks in this course•5 minutes
- Week 1 Wrap up•2 minutes
- Join the DeepLearning.AI Forum to ask questions, get support, or share amazing ideas!•2 minutes
- Lecture Notes Week 1•1 minute
- Assignment Troubleshooting Tips•5 minutes
- (Optional) Downloading your Notebook and Refreshing your Workspace•2 minutes
1 assignment•Total 30 minutes
- Week 1 Quiz•30 minutes
1 programming assignment•Total 180 minutes
- Working with generated time series•180 minutes
2 ungraded labs•Total 60 minutes
- Introduction to time series notebook (Lab 1)•30 minutes
- Forecasting notebook (Lab 2)•30 minutes
Having explored time series and some of the common attributes of time series such as trend and seasonality, and then having used statistical methods for projection, let's now begin to teach neural networks to recognize and predict on time series!
What's included
10 videos2 readings1 assignment1 programming assignment3 ungraded labs
10 videos•Total 25 minutes
- A conversation with Andrew Ng•1 minute
- Preparing features and labels•4 minutes
- Preparing features and labels (screencast)•3 minutes
- Feeding windowed dataset into neural network•2 minutes
- Single layer neural network•3 minutes
- Machine learning on time windows•1 minute
- Prediction•2 minutes
- More on single layer neural network•2 minutes
- Deep neural network training, tuning and prediction•4 minutes
- Deep neural network•3 minutes
2 readings•Total 2 minutes
- Week 2 Wrap up•1 minute
- Lecture Notes Week 2•1 minute
1 assignment•Total 30 minutes
- Week 2 Quiz•30 minutes
1 programming assignment•Total 180 minutes
- Forecasting Using Neural Networks•180 minutes
3 ungraded labs•Total 90 minutes
- Preparing features and labels notebook (Lab 1)•30 minutes
- Single layer neural network notebook (Lab 2)•30 minutes
- Deep neural network notebook (Lab 3)•30 minutes
Recurrent Neural networks and Long Short Term Memory networks are really useful to classify and predict on sequential data. This week we'll explore using them with time series...
What's included
8 videos4 readings1 assignment1 programming assignment2 ungraded labs
8 videos•Total 16 minutes
- Week 3 - A conversation with Andrew Ng•3 minutes
- Conceptual overview•3 minutes
- Shape of the inputs to the RNN•2 minutes
- Outputting a sequence•1 minute
- Lambda layers•1 minute
- Adjusting the learning rate dynamically•2 minutes
- LSTM•2 minutes
- Coding LSTMs•2 minutes
4 readings•Total 22 minutes
- More info on Huber loss•10 minutes
- Link to the LSTM lesson•10 minutes
- Week 3 Wrap up•1 minute
- Lecture Notes Week 3•1 minute
1 assignment•Total 30 minutes
- Week 3 Quiz•30 minutes
1 programming assignment•Total 180 minutes
- Forecast using RNNs or LSTMs•180 minutes
2 ungraded labs•Total 60 minutes
- RNN notebook (Lab 1)•30 minutes
- LSTM notebook (Lab 2) •30 minutes
On top of DNNs and RNNs, let's also add convolutions, and then put it all together using a real-world data series -- one which measures sunspot activity over hundreds of years, and see if we can predict using it.
What's included
11 videos9 readings1 assignment1 programming assignment2 ungraded labs
11 videos•Total 22 minutes
- Week 4 - A conversation with Andrew Ng•1 minute
- Convolutions•1 minute
- Bi-directional LSTMs•3 minutes
- Convolutions with LSTM•1 minute
- Real data - sunspots•3 minutes
- Train and tune the model•3 minutes
- Prediction•2 minutes
- Sunspots•1 minute
- Combining our tools for analysis•4 minutes
- Congratulations!•1 minute
- Specialization wrap up - A conversation with Andrew Ng•2 minutes
9 readings•Total 42 minutes
- Convolutional neural networks course•10 minutes
- More on batch sizing•10 minutes
- Lecture Notes Week 4•1 minute
- [IMPORTANT] Reminder about end of access to Lab Notebooks•2 minutes
- Wrap up•1 minute
- References•10 minutes
- Acknowledgments•1 minute
- What next?•5 minutes
- (Optional) Opportunity to Mentor Other Learners•2 minutes
1 assignment•Total 30 minutes
- Week 4 Quiz•30 minutes
1 programming assignment•Total 180 minutes
- Adding CNNs to improve forecasts•180 minutes
2 ungraded labs•Total 75 minutes
- Convolutions with LSTM notebook (Lab 1)•30 minutes
- Sunspots notebooks (Lab 2 & Lab 3)•45 minutes
Earn a career certificate
Add this credential to your LinkedIn profile, resume, or CV. Share it on social media and in your performance review.
Instructor
Offered by
Explore more from Machine Learning
- Status: Preview
- Status: Free TrialD
DeepLearning.AI
Course
- Status: Free TrialL
LearnQuest
Course
- Status: Free Trial
Why people choose Coursera for their career
Learner reviews
- 5 stars
78%
- 4 stars
15.72%
- 3 stars
3.89%
- 2 stars
1.16%
- 1 star
1.21%
Showing 3 of 5162
Reviewed on Dec 26, 2019
I'm so glad to take this course and build my knowledge regarding time-series data and modern approaches to create prognostic models. Thanks to Andrew Ng and L. Moroney to provide this course.
Reviewed on Jun 6, 2020
I really enjoyed this course, especially because it combines all different components (DNN, CONV-NET, and RNN) together in one application. I look forward to taking more courses from deeplearning.ai.
Reviewed on Jul 16, 2020
The course is fantastic. It was a bit short and with some hyperparameters tuning focus, it could have been great. Also, it seems that it is biased to show that LSTM is always superior to RNN networks.
Frequently asked questions
To access the course materials, assignments and to earn a Certificate, you will need to purchase the Certificate experience when you enroll in a course. You can try a Free Trial instead, or apply for Financial Aid. The course may offer 'Full Course, No Certificate' instead. This option lets you see all course materials, submit required assessments, and get a final grade. This also means that you will not be able to purchase a Certificate experience.
When you enroll in the course, you get access to all of the courses in the Certificate, and you earn a certificate when you complete the work. Your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile.
More questions
Financial aid available,