TensorFlow: Advanced Techniques Specialization

About TensorFlow

TensorFlow is an end-to-end open-source platform for machine learning. It has a comprehensive, flexible ecosystem of tools, libraries, and community resources that lets researchers push the state-of-the-art in ML, and developers easily build and deploy ML-powered applications. TensorFlow is commonly used for machine learning applications such as voice recognition and detection, Google Translate, image recognition, and natural language processing. 


About this Specialization

The DeepLearning.AI TensorFlow: Advanced Techniques Specialization introduces the features of TensorFlow that provide learners with more control over their model architecture and tools that help them create and train advanced ML models.

In this Specialization, you will expand your knowledge of the Functional API and build exotic non-sequential model types. You will learn how to optimize training in different environments with multiple processors and chip types and get introduced to advanced computer vision scenarios such as object detection, image segmentation, and interpreting convolutions. You will also explore generative deep learning including the ways AIs can create new content from Style Transfer to Auto Encoding, VAEs, and GANs.

 

About you

This Specialization is for early and mid-career software and machine learning engineers with a foundational understanding of TensorFlow who are looking to expand their knowledge and skill set by learning advanced TensorFlow features to build powerful models.

Looking for a place to start? Master foundational basics with the DeepLearning.AI TensorFlow Developer Professional Certificate.
Ready to deploy your models to the world? Learn how to go live with the TensorFlow: Data and Deployment Specialization.

Course 1

Custom Models, Layers, and Loss Functions with TensorFlow

Course 2

Custom and Distributed Training with TensorFlow

Course 3

Advanced Computer Vision with TensorFlow

Course 3

Apply Generative Adversarial Networks (GANs)

Course 1: Custom Models, Layers, and Loss Functions with TensorFlow

This is the first course of the TensorFlow: Advanced Techniques Specialization.

Week 1: Functional API

  • Compare Functional and Sequential APIs, discover new models you can build with the Functional API, and build a model that produces multiple outputs including a Siamese network.

Week 2: Custom Loss Functions

  • Build custom loss functions (including the contrastive loss function used in a Siamese network) in order to measure how well a model is doing and help your neural network learn from training data.

Week 3: Custom Layers

  • Build off of existing standard layers to create custom layers for your models, customize a network layer with a lambda layer, understand the differences between them, learn what makes up a custom layer, and explore activation functions.

Week 4: Custom Models

  • Build off of existing models to add custom functionality, learn how to define your own custom class instead of using the Functional or Sequential APIs, build models that can be inherited from the TensorFlow Model class, and build a residual network (ResNet) through defining a custom model class.

Bonus: Callbacks

  • Customize your model outputs and its behavior during training through custom callbacks, implement a custom callback to stop training once the callback detects overfitting, use a model checkpoint to save parameters during training, use the EarlyStopping callback to keep a model from overfitting, and become familiar with where you might want to create a custom callback.

 

Course 2: Custom and Distributed Training with TensorFlow

This is the second course of the TensorFlow: Advanced Techniques Specialization.

Week 1: Differentiation and Gradients

  • Learn about Tensor objects, the fundamental building blocks of TensorFlow, understand the difference between the eager and graph modes in TensorFlow, and learn how to use a TensorFlow tool to calculate gradients.

Week 2: Custom Training

  • Build your own custom training loops using GradientTape and TensorFlow Datasets to gain more flexibility and visibility with your model training.

Week 3: Graph Mode

  • Learn about the benefits of generating code that runs in graph mode, take a peek at what graph code looks like, and practice generating this more efficient code automatically with TensorFlow’s tools.

Week 4: Distributed Training

  • Harness the power of distributed training to process more data and train larger models, faster, get an overview of various distributed training strategies, and practice working with a strategy that trains on multiple GPU cores, and another that trains on multiple TPU cores.

Course 3: Advanced Computer Vision with TensorFlow

This is the third course of the TensorFlow: Advanced Techniques Specialization.

Week 1: Introduction to Computer Vision

  • Explore image classification, image segmentation, object localization, and object detection. Apply transfer learning to object localization and detection.

Week 2: Object Detection

  • Apply object detection models such as regional-CNN and ResNet-50, customize existing models, and build your own models to detect, localize, and label your own rubber duck images.

Week 3: Image Segmentation

  • Implement image segmentation using variations of the fully convolutional network (FCN) including U-Net and Mask-RCNN to identify and detect numbers, pets, zombies, and more.

Week 4: Visualization and Interpretation

  • Identify which parts of an image are being used by your model to make its predictions using class activation maps and saliency maps and apply these ML interpretation methods to inspect and improve the design of a famous network, AlexNet.

 

Course 4: Generative Deep Learning with TensorFlow

This is the fourth course of the TensorFlow: Advanced Techniques Specialization.

 

Frequently Asked Questions

What is TensorFlow?

TensorFlow is an end-to-end open-source platform for machine learning. It has a comprehensive, flexible ecosystem of tools, libraries, and community resources that lets researchers push the state-of-the-art in ML, and developers easily build and deploy ML-powered applications.  

What are the applications of TensorFlow?

TensorFlow is commonly used for machine learning applications such as voice recognition and detection, Google Translate, image recognition, and natural language processing.

Why is TensorFlow important?

TensorFlow is one of the most commonly used open-source libraries used for building and deploying ML models.

What is the TensorFlow: Advanced Techniques Specialization about?

The DeepLearning.AI TensorFlow: Advanced Techniques Specialization introduces the features of TensorFlow that provide learners with more control over their model architecture and tools that help them create and train advanced ML models.  

In this Specialization, you will expand your knowledge of the Functional API and build exotic non-sequential model types. You will learn how to optimize training in different environments with multiple processors and chip types and get introduced to advanced computer vision scenarios such as object detection, image segmentation, and interpreting convolutions. You will also explore generative deep learning including the ways AIs can create new content from Style Transfer to Auto Encoding, VAEs, and GANs.

I’ve already completed the DeepLearning.AI TensorFlow Developer Professional Certificate. What else will I learn in this Specialization?

The DeepLearning.AI TensorFlow Developer Professional Certificate equips you with the foundational knowledge to create entry-level TensorFlow models using the Sequential API and prepares you for the Google TensorFlow Developer Certificate exam. 

In this new TensorFlow Specialization, you will expand your skill set and take your understanding of TensorFlow techniques to the next level. You will learn how to use the Functional API for custom training, custom layers, and custom models. You will be equipped to master TensorFlow in order to build powerful applications for complex scenarios.

What will I learn in the TensorFlow Specialization?

As part of this Specialization, you will gain practical knowledge and hands-on training in advanced TensorFlow techniques such as style transfer (paint one picture in the style of another), object detection (detect where an object is in a picture), and generative machine learning (generating new images from scratch).

Course 1: Understand the underlying basis of the Functional API and build exotic non-sequential model types, custom loss functions, and layers. 

Course 2: Learn how optimization works and how to use GradientTape and Autograph. Optimize training in different environments with multiple processors and chip types.

Course 3: Practice object detection, image segmentation, and visual interpretation of convolutions.Course 4: Explore generative deep learning and how AIs can create new content, from Style Transfer through Auto Encoding and VAEs to Generative Adversarial Networks.

Who is the TensorFlow Specialization for?

This Specialization is for early and mid-career software and machine learning engineers with a foundational understanding of TensorFlow who are looking to expand their knowledge and skill set by learning advanced TensorFlow features to build powerful models.

What background knowledge is necessary?

Learners should have a working knowledge of AI and deep learning. They should have intermediate Python skills (understanding of decorators and context managers is preferred) as well as some experience with any deep learning framework (TensorFlow, Keras, or PyTorch). Learners should be proficient in basic calculus, linear algebra, and statistics.

We highly recommend that you complete the Deep Learning Specialization prior to starting this Specialization.

What will I be able to do upon completing the TensorFlow Specialization?

After completing this Specialization, you gain practical knowledge of and hands-on training in advanced TensorFlow techniques such as style transfer (paint one picture in the style of another), object detection (detect where an object is in a picture), and generative machine learning (generating new images from scratch).

Who created the TensorFlow Specialization?

This Specialization was created by Laurence Moroney. Laurence leads AI Advocacy at Google, with a vision to make AI easy for developers and to widen access to ML careers for everyone. He’s written dozens of programming books, the most recent being ‘AI and ML for Coders’ at O’Reilly. Laurence believes that MOOCs are one of the greatest ways to learn, and is excited to create TensorFlow Specializations with DeepLearning.AI on Coursera. 

When not working with technology, he’s an active member of the Science Fiction Writers of America, and has authored several sci-fi novels and comics books and a produced screenplay. Laurence is based in Washington state, where he drinks way too much coffee.

Is this a stand-alone course or a Specialization?

This is a Specialization made up of 4 courses. 

How do I take the TensorFlow Specialization?

You can enroll in the DeepLearning.AI TensorFlow: Advanced Techniques Specialization on Coursera. You will watch videos and complete assignments on Coursera as well.

Do I need to take the courses in a specific order?

We recommend taking the courses in the prescribed order for a logical and thorough learning experience.

How much does the Specialization cost?

A Coursera subscription costs $49 / month. Course 1 and Course 2 of this Specialization are available right now. Course 3 will be announced soon.

Can I audit the Specialization?

You can audit the courses in the Specialization for free. Visit the Course Page, click on ‘Enroll’ and then click on ‘Audit’ at the bottom of the page. Note that you will not receive a certificate at the end of the course if you choose to audit it for free instead of purchasing it.

Can I apply for financial aid?

Yes, Coursera provides financial aid to learners who cannot afford the fee. Visit the Coursera Course Page and click on ‘Financial Aid’ beneath the ‘Enroll’ button on the left.

Will I receive a certificate at the end of the Specialization?

You will receive a certificate at the end of each course if you pay for the courses and complete the programming assignments. There is a limit of 180 days of certificate eligibility, after which you must re-purchase the course to obtain a certificate. If you audit the course for free, you will not receive a certificate.

If you complete all n courses in the S12n and are subscribed to the Specialization, you will also receive an additional certificate showing that you completed the entire Specialization.

How long does it take to complete the Specialization?

This Specialization consists of four courses. At the rate of 5 hours a week, it typically takes 3-4  weeks to complete each course.

About the Instructor

Laurence Moroney

Laurence Moroney

AI Advocate, Google

Laurence Moroney leads AI Advocacy at Google, with a vision to make AI easy for developers and to widen access to ML careers for everyone. He’s written dozens of programming books, the most recent being ‘AI and ML for Coders’ at O’Reilly. Laurence believes that MOOCs are one of the greatest ways to learn, and is excited to create TensorFlow Specializations with DeepLearning.AI on Coursera. 

When not working with technology, he’s an active member of the Science Fiction Writers of America, and has authored several sci-fi novels and comics books and a produced screenplay. Laurence is based in Washington state, where he drinks way too much coffee

We use cookies to collect information about our website and how users interact with it. We’ll use this information solely to improve the site. You are agreeing to consent to our use of cookies if you click ‘OK’. All information we collect using cookies will be subject to and protected by our Privacy Policy, which you can view here.

OK