About this Course

70,532 recent views
Shareable Certificate
Earn a Certificate upon completion
100% online
Start instantly and learn at your own schedule.
Flexible deadlines
Reset deadlines in accordance to your schedule.
Intermediate Level
  • Basic calculus, linear algebra, stats
  • Knowledge of AI, deep learning
  • Experience with Python, TF/Keras/PyTorch framework, decorator, context manager
Approx. 31 hours to complete
English

Skills you will gain

Functional APICustom LayersCustom and Exotic Models with Functional APICustom Loss Functions
Shareable Certificate
Earn a Certificate upon completion
100% online
Start instantly and learn at your own schedule.
Flexible deadlines
Reset deadlines in accordance to your schedule.
Intermediate Level
  • Basic calculus, linear algebra, stats
  • Knowledge of AI, deep learning
  • Experience with Python, TF/Keras/PyTorch framework, decorator, context manager
Approx. 31 hours to complete
English

Offered by

Placeholder

DeepLearning.AI

Syllabus - What you will learn from this course

Week
1

Week 1

8 hours to complete

Functional APIs

8 hours to complete
11 videos (Total 47 min), 5 readings, 2 quizzes
11 videos
A conversation with Andrew Ng: Overview of course 14m
Welcome to the course23s
Introduction to the Functional APIs6m
Declaring and stacking layers2m
Branching models2m
Creating a Multi-Output model4m
Multi-Output code walkthrough5m
Siamese network: a Multiple-Input model 2m
Coding a Multi-Input Siamese network4m
Siamese network code walkthrough8m
5 readings
Connect with your mentors and fellow learners on Slack!10m
Learn more about the Inception Model Architecture 10m
Energy efficiency dataset3m
References about the Siamese network3m
Reference "The distance between two vectors"3m
1 practice exercise
Functional API30m
Week
2

Week 2

7 hours to complete

Custom Loss Functions

7 hours to complete
9 videos (Total 23 min), 2 readings, 2 quizzes
9 videos
Creating a custom loss function3m
Coding the Huber Loss function2m
Huber Loss code walkthrough2m
Adding hyperparameters to custom loss functions2m
Turning loss functions into classes1m
Huber Object Loss code walkthrough3m
Contrastive Loss3m
Coding Contrastive Loss2m
2 readings
Huber Loss reference5m
Reference: Dimensionality reduction by Learning an Invariant Mapping3m
1 practice exercise
Custom Loss30m
Week
3

Week 3

7 hours to complete

Custom Layers

7 hours to complete
10 videos (Total 31 min)
10 videos
Introduction to Lambda Layers2m
Custom Functions from Lambda Layers1m
Exploring custom Relu with Lambda Layers 4m
Architecture of a Custom Layer2m
Coding your own custom Dense Layer4m
Training a neural network with your Custom Layer2m
Custom Layer code walkthrough5m
Activating your Custom Layer3m
Custom Layer with activation code walkthrough3m
1 practice exercise
Custom Layers30m
Week
4

Week 4

6 hours to complete

Custom Models

6 hours to complete
7 videos (Total 29 min), 1 reading, 2 quizzes
7 videos
Complex architectures with the Functional API3m
Coding a Wide and Deep model2m
Using the Model class to simplify architectures3m
Understanding Residual networks7m
Coding a Residual network with the Model class5m
ResNet code walkthrough5m
1 reading
Residual networks lectures (optional)10m
1 practice exercise
Custom Models30m

Reviews

TOP REVIEWS FROM CUSTOM MODELS, LAYERS, AND LOSS FUNCTIONS WITH TENSORFLOW

View all reviews

About the TensorFlow: Advanced Techniques Specialization

TensorFlow: Advanced Techniques

Frequently Asked Questions

More questions? Visit the Learner Help Center.