Buy Now AED 170.99 + VAT

Monthly Subscription Starting at AED 99 + VAT

Sequences, Time Series and Prediction
  • Level Professional
  • Duration 23 hours
  • Course by DeepLearning.AI
  • Offered by

About

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 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.

Modules

Introduction

    • 1 Videos
    • 1 Readings
Show info about module content

1 Videos

  • Introduction: A conversation with Andrew Ng

1 Readings

  • Welcome to the course!

Sequences and Prediction

    • 9 Videos
    • 3 Readings
    • 2 Lab
    • 1 Assignment
Show info about module content

1 Assignment

  • Week 1 Quiz

2 Labs

  • Introduction to time series notebook (Lab 1)
  • Forecasting notebook (Lab 2)

9 Videos

  • 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

3 Readings

  • About the notebooks in this course
  • [IMPORTANT] Have questions, issues or ideas? Join our Forum!
  • Week 1 Wrap up

Lecture Notes (Optional)

    • 1 Readings
Show info about module content

1 Readings

  • Lecture Notes Week 1

Weekly Assignment - Create and predict synthetic data

    • 2 Readings
    • 1 Programming
Show info about module content

1 Programming

  • Working with generated time series

2 Readings

  • Assignment Troubleshooting Tips
  • (Optional) Downloading your Notebook and Refreshing your Workspace

Deep Neural Networks for Time Series

    • 10 Videos
    • 1 Readings
    • 3 Lab
    • 1 Assignment
Show info about module content

1 Assignment

  • Week 2 Quiz

3 Labs

  • Preparing features and labels notebook (Lab 1)
  • Single layer neural network notebook (Lab 2)
  • Deep neural network notebook (Lab 3)

10 Videos

  • A conversation with Andrew Ng
  • Preparing features and labels
  • Preparing features and labels (screencast)
  • 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

1 Readings

  • Week 2 Wrap up

Lecture Notes (Optional)

    • 1 Readings
Show info about module content

1 Readings

  • Lecture Notes Week 2

Weekly Assignment - Prediction with a DNN

    • 1 Programming
Show info about module content

1 Programming

  • Forecasting Using Neural Networks

Recurrent Neural Networks for time series

    • 8 Videos
    • 3 Readings
    • 2 Lab
    • 1 Assignment
Show info about module content

1 Assignment

  • Week 3 Quiz

2 Labs

  • RNN notebook (Lab 1)
  • LSTM notebook (Lab 2)

8 Videos

  • 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
  • LSTM
  • Coding LSTMs

3 Readings

  • More info on Huber loss
  • Link to the LSTM lesson
  • Week 3 Wrap up

Lecture Notes (Optional)

    • 1 Readings
Show info about module content

1 Readings

  • Lecture Notes Week 3

Weekly Assignment - Using layers for sequence processing

    • 1 Programming
Show info about module content

1 Programming

  • Forecast using RNNs or LSTMs

Real-world time series data

    • 9 Videos
    • 2 Readings
    • 2 Lab
    • 1 Assignment
Show info about module content

1 Assignment

  • Week 4 Quiz

2 Labs

  • Convolutions with LSTM notebook (Lab 1)
  • Sunspots notebooks (Lab 2 & Lab 3)

9 Videos

  • Week 4 - A conversation with Andrew Ng
  • Convolutions
  • Bi-directional LSTMs
  • Convolutions with LSTM
  • Real data - sunspots
  • Train and tune the model
  • Prediction
  • Sunspots
  • Combining our tools for analysis

2 Readings

  • Convolutional neural networks course
  • More on batch sizing

Lecture Notes (Optional)

    • 1 Readings
Show info about module content

1 Readings

  • Lecture Notes Week 4

End of Access to Lab Notebooks

    • 1 Readings
Show info about module content

1 Readings

  • [IMPORTANT] Reminder about end of access to Lab Notebooks

Weekly Assignment - Adding Convolutions

    • 1 Programming
Show info about module content

1 Programming

  • Adding CNNs to improve forecasts

Course 4 Wrap up

    • 1 Videos
    • 1 Readings
Show info about module content

1 Videos

  • Congratulations!

1 Readings

  • Wrap up

References and Acknowledgments

    • 2 Readings
Show info about module content

2 Readings

  • References
  • Acknowledgments

TensorFlow in practice has come to an end

    • 1 Videos
    • 2 Readings
Show info about module content

1 Videos

  • Specialization wrap up - A conversation with Andrew Ng

2 Readings

  • What next?
  • (Optional) Opportunity to Mentor Other Learners

Auto Summary

"Sequences, Time Series and Prediction" is a professional-level course in Data Science & AI, offered by Coursera. Taught by Andrew Ng, this course focuses on building time series models using TensorFlow. Learners will prepare data, utilize RNNs and 1D ConvNets for predictions, and create a sunspot prediction model. The 1380-minute course is ideal for software developers aiming to construct scalable AI algorithms. Subscription options include Starter, Professional, and Paid plans.

Laurence Moroney
Instructor

Laurence Moroney