Get updates on Eligibility, Admission, Placements Fees Structure
Quick Facts
| Medium Of Instructions | Mode Of Learning | Mode Of Delivery |
|---|---|---|
| English | Self Study | Video and Text Based |
Course Overview
The Imperial College of London offers the Getting Started With TensorFlow 2 online course in conjunction with Coursera. Achieving certification in courses offered by this esteemed institution gives you an inclusive educational experience and superior digital technology.
The Getting Started With TensorFlow 2 certification course has modules spread out over five weeks, which candidates can complete in approximately 26 hours. Dr Kevin Webster, a Senior Teaching Fellow in Statistics at the Imperial College London, instructs the certification course.
An intermediate-level course, the Getting Started With TensorFlow 2 training will teach you the fundamentals concepts of TensorFlow. You will become fully adept in developing deep learning models and using them to evaluate, train, and make predictions.
Furthermore, the Getting Started With TensorFlow 2 certification course promotes interaction and improvement of one’s core abilities with a comprehensive curriculum and intermittent assignments. You can self-assess through these mediums and grasp the course contents at your own pace. Finally, Coursera awards you with a certificate upon successful completion.
The Highlights
- 100% online
- Shareable certificate
- Course videos
- Readings
- Intermediate level course
- Financial Aid available
- Lectures in English and subtitles available in English
- Fast completion (approximately 26 hours)
- Flexible deadlines
- Capstone project
Programme Offerings
- Course completion certificate
- discussion forum
- Email Updates and Communication
- 26 Hours learning
- Shareable Certificate
- Graded Programming Assignments.
Courses and Certificate Fees
| Certificate Availability | Certificate Providing Authority |
|---|---|
| yes | Imperial College, LondonCoursera |
Getting Started With TensorFlow 2 fees details:
Particulars | Amount |
Course Fee, 1 Month | Rs. 4,115 |
Course Fee, 3 Month | Rs. 8,230 |
Course Fee, 6 Month | Rs. 12,345 |
Eligibility Criteria
For satisfactory completion of the Getting Started With TensorFlow 2 certification by Coursera course, candidates need to know the fundamentals of python 3. Candidates should also have proficiency in the basics of machine learning and related concepts like validation, model selection, and more. Additionally, they should have a complete understanding of deep learning fundamentals.
What you will learn
Upon completion of all the modules in the Getting Started With TensorFlow 2 certification syllabus, you will be able to:
- Develop more in-depth knowledge in the field of machine learning
- Build deep learning models with the help of TensorFlow
- Use Sequential API to build, train, predict and examine deep learning models
- Load and save models as well as the implementation of callbacks
- Apply the concepts with coding tutorials
Who it is for
The Getting Started With TensorFlow 2 course by Coursera is for the following professionals:
- Deep Learning Engineers and students
- Machine Learning Engineers and aspiring students
Admission Details
To apply for the Getting Started With TensorFlow 2 classes:
Step 1. Go to the Coursera website- https://www.coursera.org/
Step 2.Find ‘Getting Started With TensorFlow 2.
Step3. Click on the ‘Enrol for Free’ option.
Step 4. Follow the instructions and enroll for the course. You can sign up using your email ID or Google account to start learning.
Application Details
Use your gmail or another Google account to sign up for the TensorFlow 2 Coursera course. You can choose the enrollment type you prefer and access course materials and certificate accordingly.
The Syllabus
Videos
- Introduction to the course
- Welcome to week 1
- Hello TensorFlow!
- [Coding tutorial] Hello TensorFlow!
- What's new in TensorFlow
- Interview with Laurence Moroney
- Introduction to Google Colab
- [Coding tutorial] Introduction to Google Colab
- TensorFlow documentation
- TensorFlow installation
- [Coding tutorial] pip installation
- [Coding tutorial] Running TensorFlow with Docker
- Upgrading from TensorFlow
- [Coding tutorial] Upgrading from TensorFlow 1
Readings
- About Imperial College & the team
- How to be successful in this course
- Grading policy
- Additional readings & helpful references
- What is TensorFlow?
- Google Colab resources
- TensorFlow documentation
- Upgrade TensorFlow 1.x Notebooks
Discussion Prompt
- Introduce yourself
Ungraded Lab
- [Coding tutorial] Hello TensorFlow!
Plugin
- Pre-Course Survey
Videos
- Welcome to week 2 - The Sequential model API
- What is Keras?
- Building a Sequential model
- [Coding tutorial] Building a Sequential model
- Convolutional and pooling layers
- [Coding tutorial] Convolutional and pooling layers
- The compile method
- [Coding tutorial] The compile method
- The fit method
- [Coding tutorial] The fit method
- The evaluate and predict methods
- [Coding tutorial] The evaluate and predict methods
- Wrap up and introduction to the programming assignment
Assignments
- [Knowledge check] Feedforward and convolutional neural networks
- [Knowledge check] Optimisers, loss functions and metrics
Programming Assignment
- CNN classifier for the MNIST dataset
Ungraded Labs
- [Coding tutorial] Building a Sequential model
- [Coding tutorial] Convolutional and pooling layers
- [Reading] Adding weight initialisers
- [Coding tutorial] The compile method
- [Reading] Metrics in Keras
- [Coding tutorial] The fit method
- [Coding tutorial] The evaluate and predict methods
- CNN classifier for the MNIST dataset
Videos
- Welcome to week 3 - Validation, regularisation and callbacks
- Interview with Andrew Ng
- Validation sets
- [Coding Tutorial] Validation sets
- Model regularisation
- [Coding Tutorial] Model regularisation
- Introduction to callbacks
- [Coding tutorial] Introduction to callbacks
- Early stopping and patience
- [Coding tutorial] Early stopping and patience
- Wrap up and introduction to the programming assignment
Assignment
- [Knowledge check] Validation and regularisation
Programming Assignment
- Model validation on the Iris dataset
Ungraded Labs
- [Coding Tutorial] Validation sets
- [Coding Tutorial] Model regularisation
- [Reading] Batch normalisation layers
- [Coding tutorial] Introduction to callbacks
- [Reading] The logs dictionary
- [Coding tutorial] Early stopping and patience
- [Reading] Additional callbacks
- Model validation on the Iris dataset
Videos
- Welcome to week 4 - Saving and loading models
- Saving and loading model weights
- [Coding tutorial] Saving and loading model weights
- Model saving criteria
- [Coding tutorial] Model saving criteria
- Saving the entire model
- [Coding tutorial] Saving the entire model
- Loading pre-trained Keras models
- [Coding tutorial] Loading pre-trained Keras models
- TensorFlow Hub modules
- [Coding tutorial] TensorFlow Hub modules
- Wrap up and introduction to the programming assignment
Programming Assignment
- Saving and loading models
Ungraded Labs
- [Coding tutorial] Saving and loading model weights
- [Reading] Explanation of saved files
- [Coding tutorial] Model saving criteria
- [Coding tutorial] Saving the entire model
- [Reading] Saving model architecture only
- [Coding tutorial] Loading pre-trained Keras models
- [Coding tutorial] TensorFlow Hub modules
- Saving and loading models
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)
It depends on the type of enrollment you opted for. If you take a course in audit mode, you will get access to maximum course materials for free. Those who want access to graded assignments and earn a Certificate, need to purchase the Certificate experience. This can be done during, or after your audit.
Paid subscribers get access to all the courses that are a part of the Specialization. On successful completion of the course, Coursera will add your electronic Certificate to your Accomplishments page. Candidates can print the Certificate or add it to their LinkedIn profile.
Yes, Coursera offers financial support to candidates who cannot pay the fee for the Getting Started With TensorFlow 2 course. You can apply for financial assistance by clicking on the link that is below the enrol button on the left. Once you are approved, Coursera will notify you.
The Getting Started With TensorFlow 2 course does not offer university credit. However, some universities may accept Course Certificates for credit. You can get in touch with your university to confirm the same and accordingly submit the course certificate.
This is a flexible course where one can easily reset the deadline and complete the assignments as well as lectures at their own pace.