Course Summary
Learn how to use TensorFlow to build sequence models and time series models for prediction.Key Learning Points
- Understand how to use TensorFlow for building sequence models and time series models
- Learn how to preprocess data for use in sequence and time series models
- Explore techniques for prediction using sequence and time series models
Related Topics for further study
Learning Outcomes
- Ability to build sequence models and time series models using TensorFlow
- Understanding of data preprocessing techniques for sequence and time series models
- Knowledge of various prediction techniques for sequence and time series models
Prerequisites or good to have knowledge before taking this course
- Familiarity with Python programming language
- Basic understanding of machine learning concepts
Course Difficulty Level
IntermediateCourse Format
- Online
- Self-paced
Similar Courses
- Applied Data Science with Python
- Machine Learning
Related Education Paths
Notable People in This Field
- Andrew Ng
- François Chollet
Related Books
Description
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.
Knowledge
- 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
Outline
- Sequences and Prediction
- Introduction, A conversation with Andrew Ng
- Time series examples
- Machine learning applied to time series
- Common patterns in time series
- Introduction to time series
- Train, validation and test sets
- Metrics for evaluating performance
- Moving average and differencing
- Trailing versus centered windows
- Forecasting
- Introduction to time series notebook
- Forecasting notebook
- Week 1 Wrap up
- Deep Neural Networks for Time Series
- A conversation with Andrew Ng
- Preparing features and labels
- Preparing features and labels
- Feeding windowed dataset into neural network
- Single layer neural network
- Machine learning on time windows
- Prediction
- More on single layer neural network
- Deep neural network training, tuning and prediction
- Deep neural network
- Preparing features and labels notebook
- Sequence bias
- Single layer neural network notebook
- Deep neural network notebook
- Week 2 Wrap up
- Recurrent Neural Networks for Time Series
- Week 3 - A conversation with Andrew Ng
- Conceptual overview
- Shape of the inputs to the RNN
- Outputting a sequence
- Lambda layers
- Adjusting the learning rate dynamically
- RNN
- LSTM
- Coding LSTMs
- More on LSTM
- More info on Huber loss
- RNN notebook
- Link to the LSTM lesson
- LSTM notebook
- Week 3 Wrap up
- Real-world time series data
- Week 4 - A conversation with Andrew Ng
- Convolutions
- Bi-directional LSTMs
- LSTM
- Real data - sunspots
- Train and tune the model
- Prediction
- Sunspots
- Combining our tools for analysis
- Congratulations!
- Specialization wrap up - A conversation with Andrew Ng
- Convolutional neural networks course
- More on batch sizing
- LSTM notebook
- Sunspots notebook
- Wrap up
- What next?
- (Optional) Opportunity to Mentor Other Learners
Summary of User Reviews
Learn about TensorFlow Sequences, Time Series and Prediction in this highly-rated course on Coursera. Students praise the course's comprehensive coverage of the topic, which includes real-world examples and practical exercises.Key Aspect Users Liked About This Course
Comprehensive coverage of the topicPros from User Reviews
- Real-world examples provide practical context for learning
- Instructors are knowledgeable and engaging
- Course materials are well-organized and easy to follow
- Assignments and quizzes help reinforce key concepts
- Great introduction to TensorFlow for those with no prior experience
Cons from User Reviews
- Some users found the pace of the course to be too slow
- Not enough focus on advanced topics
- Lectures can be a bit dry at times
- Some of the code examples are outdated
- Not enough emphasis on best practices or real-world challenges
Laurence Moroney
4.7 Raiting
Machine Learning with R Programming
- 3.3
-
![]()
![]()
![]()
![]()
![]()
Learn in Detail How to execute Machine Learning Algorithms in R Programming...
Using SAS Viya REST APIs with Python and R
- 0.0
-
![]()
![]()
![]()
![]()
![]()
SAS Viya is an in-memory distributed environment used to analyze big data quickly and efficiently. Course Overview Course Overview Learner Prerequisites...
Bioinformatic Methods II
- 4.7
-
![]()
![]()
![]()
![]()
![]()
Large-scale biology projects such as the sequencing of the human genome and gene expression surveys using RNA-seq, microarrays and other technologies have created a wealth of data for biologists....
Single Variable Calculus
- 4.6
-
![]()
![]()
![]()
![]()
![]()
Calculus is one of the grandest achievements of human thought, explaining everything from planetary orbits to the optimal size of a city to the periodicity of a heartbeat....
