About this Course
31,663 recent views

100% online

Start instantly and learn at your own schedule.

Flexible deadlines

Reset deadlines in accordance to your schedule.

Intermediate Level

Approx. 17 hours to complete

Suggested: 4 weeks of study, 4-5 hours/week...

English

Subtitles: English

Skills you will gain

ForecastingMachine LearningTensorflowTime Seriesprediction

100% online

Start instantly and learn at your own schedule.

Flexible deadlines

Reset deadlines in accordance to your schedule.

Intermediate Level

Approx. 17 hours to complete

Suggested: 4 weeks of study, 4-5 hours/week...

English

Subtitles: English

Syllabus - What you will learn from this course

Week
1
1 hour to complete

Sequences and Prediction

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!

...
10 videos (Total 33 min), 4 readings, 1 quiz
10 videos
Time series examples4m
Machine learning applied to time series1m
Common patterns in time series5m
Introduction to time series4m
Train, validation and test sets3m
Metrics for evaluating performance2m
Moving average and differencing2m
Trailing versus centered windows1m
Forecasting4m
4 readings
Notebook link10m
Introduction to time series notebook10m
Forecasting notebook10m
Week 1 outro10m
1 practice exercise
Week 1 Quiz
Week
2
1 hour to complete

Deep Neural Network for time series

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!

...
10 videos (Total 27 min), 5 readings, 1 quiz
10 videos
Preparing features and labels4m
Preparing features and labels3m
Feeding windowed dataset into neural network2m
Single layer neural network2m
Machine learning on time windows37s
Prediction2m
More on single layer neural network2m
Deep neural network training, tuning and prediction4m
Deep neural network3m
5 readings
Preparing features and labels notebook10m
Sequence bias10m
Single layer neural network notebook10m
Deep neural network notebook10m
Week 2 outro10m
1 practice exercise
Week 2 Quiz
Week
3
1 hour to complete

Recurrent Neural Networks for time series

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...

...
10 videos (Total 21 min), 5 readings, 1 quiz
10 videos
Conceptual overview2m
Shape of the inputs to the RNN2m
Outputting a Sequence1m
Lambda layers1m
Adjusting the learning rate dynamically2m
RNN1m
LSTM1m
Coding LSTMs2m
LSTM1m
5 readings
More info on Huber loss10m
RNN notebook10m
Link to the LSTM lesson10m
LSTM notebook10m
Week 3 outro10m
1 practice exercise
Week 3 Quiz
Week
4
1 hour to complete

Real-world time series data

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.

...
11 videos (Total 24 min), 5 readings, 1 quiz
11 videos
Convolutions58s
Bi-directional LSTMs3m
LSTM1m
Real data - sunspots3m
Train and tune the model3m
Prediction1m
Sunspots1m
Combining our tools for analysis3m
Congratulations!38s
Specialization outro - A conversation with Andrew Ng2m
5 readings
Convolutional neural networks course10m
More on batch sizing10m
LSTM notebook10m
Sunspots notebook10m
Course 4 outro10m
1 practice exercise
Week 4 Quiz

Instructor

Avatar

Laurence Moroney

AI Advocate
Google Brain

About deeplearning.ai

deeplearning.ai is Andrew Ng's new venture which amongst others, strives for providing comprehensive AI education beyond borders....

About the TensorFlow in Practice Specialization

Discover the tools software developers use to build scalable AI-powered algorithms in TensorFlow, a popular open-source machine learning framework. In this four-course Specialization, you’ll explore exciting opportunities for AI applications. Begin by developing an understanding of how to build and train neural networks. Improve a network’s performance using convolutions as you train it to identify real-world images. You’ll teach machines to understand, analyze, and respond to human speech with natural language processing systems. Learn to process text, represent sentences as vectors, and input data to a neural network. You’ll even train an AI to create original poetry! AI is already transforming industries across the world. After finishing this Specialization, you’ll be able to apply your new TensorFlow skills to a wide range of problems and projects. Courses 1-3 are available now, with Course 4 launching in July....
TensorFlow in Practice

Frequently Asked Questions

  • Once you enroll for a Certificate, you’ll have access to all videos, quizzes, and programming assignments (if applicable). Peer review assignments can only be submitted and reviewed once your session has begun. If you choose to explore the course without purchasing, you may not be able to access certain assignments.

  • When you enroll in the course, you get access to all of the courses in the Specialization, 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. If you only want to read and view the course content, you can audit the course for free.

More questions? Visit the Learner Help Center.