Probabilistic Deep Learning with TensorFlow 2
Develop your expertise in the probabilistic aspects of deep learning by acquiring the knowledge of the fundamental aspects of TensorFlow 2.
Expert
Online
5 Hours
1,699 INR Quick Facts
| Medium Of Instructions | Mode Of Learning | Mode Of Delivery |
|---|---|---|
| English | Self Study | Video and Text Based |
Course Overview
The ‘Probabilistic Deep Learning with TensorFlow 2’ online course is a study about the building of probabilistic models with TensorFlow and the incorporation of probabilistic distributions into deep learning models such as Bayesian neural networks, normalizing flows, and variational autoencoders. This certification course is provided by the Coursera online education platform and the course modules are developed by the Imperial College London.
This program is an overview of the TensorFlow Probabilistic Library and is scheduled to be completed in five weeks. The classes are guided by Dr. Kevin Webster(Senior Teaching fellow in Statistics) from the faculty of natural sciences at the department of mathematics in Imperial College London.
The ‘Probabilistic Deep Learning with TensorFlow 2’ enables students to receive a course completion certificate and the opportunity to learn the course at the preferred pace. The students are engaged with learning methodologies such as video lectures, graded assignments, and quizzes for evaluation.
The Highlights
- Online mode
- Advanced level program
- Audit mode
- EMI options
- Financial Aid
- Flexible deadlines
- Shareable certificate
- Subtitles in Arabic, French, Portuguese (European), Italian, Vietnamese, German, Russian, English, Spanish
Programme Offerings
- videos
- Reading
- Practice Exercises
- Course Modules
- quizzes
- Graded Programming Assignments
- Capstone Project
- Course Certificate.
Courses and Certificate Fees
| Certificate Availability | Certificate Providing Authority |
|---|---|
| yes | Coursera |
The fees for the course Probabilistic Deep Learning with TensorFlow 2 is -
| Head | Amount in INR |
| 1 month | Rs. 1,699 |
| 3 month | Rs. 3,499 |
| 6 month | Rs. 5,199 |
Eligibility Criteria
The ‘Probabilistic Deep Learning with TensorFlow 2’ online certification course requires the students to know the fundamental aspects of machine learning, understand the deep learning domain, and the knowledge of probability and statistics.
Certificate qualifying details
The students of the ‘Probabilistic Deep Learning with TensorFlow 2’ certification by Coursera will receive a course certificate from the Imperial College London after completion of the online classes, graded quizzes, and graded programming assignments successfully at the end of the course.
What you will learn
The ‘Probabilistic Deep Learning with TensorFlow 2’ certification syllabus is created for the students to gain professional skills and knowledge with the probabilistic neural network, aspects of deep learning, concepts of a generative model, techniques involved in TensorFlow, and the Probabilistic Programming Language(PRPL). By the end of the training program, students will be able to form a variational autoencoder algorithm to make a generative model of a synthetic image dataset built by themselves.
Who it is for
The ‘Probabilistic Deep Learning with TensorFlow 2’ online certification course is designed for the students, research associates, and industry professionals of the domain who wish to enhance their knowledge with the concepts and techniques involved in deep learning with TensorFlow.
Admission Details
The registration process for the ‘Probabilistic Deep Learning with TensorFlow 2’ online classes is done through the course website as per the following,
Step 1: Find the course page using the link,
https://www.coursera.org/learn/probabilistic-deep-learning-with-tensorflow2
Step 2: Choose the ‘Enroll For Free’ option.
Step 3: Fill in the relevant details.
Step 4: Complete the registration and join the course.
Application Details
- The applicants for the ‘Probabilistic Deep Learning with TensorFlow 2’ online program should enter their relevant details on the registration page such as name, email address, user name, and password of the Coursera account or can create a new account.
- They can also sign in using the valid Google, Facebook, or Microsoft account IDs.
The Syllabus
Videos
- Welcome to Probabilistic Deep Learning with TensorFlow 2
- Interview with Paige Bailey
- The TensorFlow Probability library
- Univariate distributions
- [Coding tutorial] Univariate distributions
- Multivariate distributions
- [Coding tutorial] Multivariate distributions
- The Independent distribution
- [Coding tutorial] The Independent distribution
- Sampling and log probs
- [Coding tutorial] Sampling and log probs
- Trainable distributions
- [Coding tutorial] Trainable distributions
- Wrap up and introduction to the programming assignment
Readings
- About Imperial College & the team
- How to be successful in this course
- Grading policy
- Additional readings & helpful references
Quiz
- Standard distributions
Programming Assignment
- Naive Bayes and logistic regression
Discussion Prompt
- Introduce yourself
Ungraded Labs
- Univariate distributions
- Multivariate distributions
- Multivariate Gaussian with full covariance
- The Independent distribution
- Broadcasting rules
- Sampling and log probs
- Trainable distributions
- Naive Bayes and logistic regression
Plugin
- Pre-Course Survey
Videos
- Welcome to week 2 - Probabilistic layers and Bayesian neural networks
- The need for uncertainty in deep learning models
- The DistributionLambda layer
- [Coding tutorial] The DistributionLambda layer
- Probabilistic layers
- [Coding tutorial] Probabilistic layers
- The DenseVariational layer
- [Coding tutorial] The DenseVariational layer
- Reparameterization layers
- [Coding tutorial] Reparameterization layers
- Wrap up and introduction to the programming assignment
Quiz
- Sources of uncertainty
Programming Assignment
- Bayesian convolutional neural network
Ungraded Labs
- Maximum likelihood estimation
- The DistributionLambda layer
- Probabilistic layers
- Bayes by backprop
- The DenseVariational layer
- Reparameterization layers
- Bayesian convolutional neural network
Videos
- Welcome to week 3 - Bijectors and normalising flows
- Interview with Doug Kelly
- Bijectors
- [Coding tutorial] Bijectors
- The TransformedDistribution class
- [Coding tutorial] The Transformed Distribution class
- Subclassing bijectors
- [Coding tutorial] Subclassing bijectors
- Autoregressive flows
- RealNVP
- [Coding tutorial] Normalising flows
- Wrap up and introduction to the programming assignment
Quiz
- Change of variables formula
Programming Assignment
- RealNVP
Ungraded Labs
- Change of variables formula
- Bijectors
- Scale bijectors and LinearOperator
- The Transformed Distribution class
- Subclassing bijectors
- Autoregressive flows and RealNVP
- Normalising flows
- RealNVP
Videos
- Welcome to week 4 - Variational autoencoders
- Encoders and decoders
- [Coding tutorial] Encoders and decoders
- Minimising KL divergence
- [Coding tutorial] Minimising KL divergence
- Maximising the ELBO
- [Coding tutorial] Maximising the ELBO
- KL divergence layers
- [Coding tutorial] KL divergence layers
- Wrap up and introduction to the programming assignment
Quiz
- Variational autoencoders
Programming Assignment
- Variational autoencoder for Celeb-A
Ungraded Labs
- Variational autoencoders
- Encoders and decoders
- Kullback-Leibler divergence
- Minimising KL divergence
- Full covariance Gaussian approximation
- Maximising the ELBO
- KL divergence layers
- Variational autoencoder for Celeb-A
Videos
- Welcome to the Capstone Project
- Goodbye video
Peer Review
- Capstone Project
Ungraded Lab
- Capstone Project
Plugin
- Post-Course Survey
Instructors
Imperial College, London Frequently Asked Questions (FAQ's)
The course is five weeks.
Yes, you can learn the course on your own.
The course is provided by Coursera and Imperial College London.
This advanced program requires the students to know concepts of Python, machine learning, deep learning, statistics, and probability.
The online shareable certificate is issued by Coursera and the Imperial College of London.