About this Course

20,567 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.
Advanced Level

* Python 3

* Knowledge of general machine learning concepts

* Knowledge of the field of deep learning

* Probability and statistics

Approx. 52 hours to complete
English

Skills you will gain

Probabilistic Neural NetworkDeep LearningGenerative ModelTensorflowProbabilistic Programming Language (PRPL)
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.
Advanced Level

* Python 3

* Knowledge of general machine learning concepts

* Knowledge of the field of deep learning

* Probability and statistics

Approx. 52 hours to complete
English

Offered by

Placeholder

Imperial College London

Syllabus - What you will learn from this course

Week
1

Week 1

12 hours to complete

TensorFlow Distributions

12 hours to complete
14 videos (Total 92 min), 4 readings, 2 quizzes
14 videos
Interview with Paige Bailey7m
The TensorFlow Probability library2m
Univariate distributions8m
[Coding tutorial] Univariate distributions6m
Multivariate distributions6m
[Coding tutorial] Multivariate distributions5m
The Independent distribution6m
[Coding tutorial] The Independent distribution12m
Sampling and log probs6m
[Coding tutorial] Sampling and log probs10m
Trainable distributions5m
[Coding tutorial] Trainable distributions11m
Wrap up and introduction to the programming assignment1m
4 readings
About Imperial College & the team10m
How to be successful in this course10m
Grading policy10m
Additional readings & helpful references10m
1 practice exercise
[Knowledge check] Standard distributions30m
Week
2

Week 2

12 hours to complete

Probabilistic layers and Bayesian neural networks

12 hours to complete
11 videos (Total 110 min)
11 videos
The need for uncertainty in deep learning models3m
The DistributionLambda layer7m
[Coding tutorial] The DistributionLambda layer10m
Probabilistic layers9m
[Coding tutorial] Probabilistic layers15m
The DenseVariational layer12m
[Coding tutorial] The DenseVariational layer20m
Reparameterization layers8m
[Coding tutorial] Reparameterization layers19m
Wrap up and introduction to the programming assignment1m
1 practice exercise
Sources of uncertainty30m
Week
3

Week 3

13 hours to complete

Bijectors and normalising flows

13 hours to complete
12 videos (Total 93 min)
12 videos
Interview with Doug Kelly10m
Bijectors7m
[Coding tutorial] Bijectors9m
The TransformedDistribution class10m
[Coding tutorial] The Transformed Distribution class8m
Subclassing bijectors5m
[Coding tutorial] Subclassing bijectors9m
Autoregressive flows10m
RealNVP8m
[Coding tutorial] Normalising flows10m
Wrap up and introduction to the programming assignment1m
1 practice exercise
Change of variables formula30m
Week
4

Week 4

13 hours to complete

Variational autoencoders

13 hours to complete
10 videos (Total 77 min)
10 videos
Encoders and decoders5m
[Coding tutorial] Encoders and decoders6m
Minimising KL divergence10m
[Coding tutorial] Minimising KL divergence7m
Maximising the ELBO13m
[Coding tutorial] Maximising the ELBO10m
KL divergence layers8m
[Coding tutorial] KL divergence layers10m
Wrap up and introduction to the programming assignment1m
1 practice exercise
Variational autoencoders30m

About the TensorFlow 2 for Deep Learning Specialization

TensorFlow 2 for Deep Learning

Frequently Asked Questions

More questions? Visit the Learner Help Center.