About this Course

17,678 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. 24 hours to complete
English

Skills you will gain

Distribution StrategiesCustom Training LoopsBasic Tensor FunctionalityGradientTape for Optimization
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. 24 hours to complete
English

Offered by

Placeholder

DeepLearning.AI

Syllabus - What you will learn from this course

Week
1

Week 1

5 hours to complete

Differentiation and Gradients

5 hours to complete
12 videos (Total 51 min), 2 readings, 2 quizzes
12 videos
What is a tensor?4m
Creating tensors in code6m
Math operations with tensors1m
Basic Tensors code walkthrough4m
Broadcasting, operator overloading and Numpy compatibility6m
Evaluating variables and changing data types4m
Gradient Tape4m
Gradient Descent using Gradient Tape4m
Calculate gradients on higher order functions4m
Persistent=true and higher order gradients2m
Gradient Tape basics code walkthrough3m
2 readings
Connect with your mentors and fellow learners on Slack!10m
Reference: CNN for visual recognition10m
1 practice exercise
Tensors and Gradient Tape30m
Week
2

Week 2

4 hours to complete

Custom Training

4 hours to complete
8 videos (Total 46 min), 1 reading, 2 quizzes
8 videos
Loss and gradient descent4m
Define Training Loop and Validate Model2m
Training Basics code walkthrough5m
Training steps and data pipeline4m
Define the training loop4m
Gradients, metrics, and validation4m
Fashion MNIST Custom Training Loop code walkthrough15m
1 reading
Reference: tf.keras.metrics10m
1 practice exercise
Custom Training30m
Week
3

Week 3

5 hours to complete

Graph Mode

5 hours to complete
6 videos (Total 35 min), 1 reading, 2 quizzes
6 videos
Generating graph code4m
AutoGraph Basics code walkthrough5m
Control dependencies and flows4m
Loops and tracing variables4m
AutoGraph code walkthrough11m
1 reading
Reference: Fizz Buzz10m
1 practice exercise
AutoGraph30m
Week
4

Week 4

10 hours to complete

Distributed Training

10 hours to complete
9 videos (Total 56 min), 3 readings, 3 quizzes
9 videos
Types of distribution strategies3m
Converting code to the Mirrored Strategy4m
Mirrored Strategy code walkthrough4m
Custom Training for Multiple GPU Mirrored Strategy5m
Multi GPU Mirrored Strategy code walkthrough13m
TPU Strategy6m
TPU Strategy code walkthrough10m
Other Distributed Strategies4m
3 readings
References used in Other Distributed Strategies10m
References 10m
Acknowledgments10m
1 practice exercise
Distributed Strategy30m

About the TensorFlow: Advanced Techniques Specialization

TensorFlow: Advanced Techniques

Frequently Asked Questions

More questions? Visit the Learner Help Center.