Deep Learning with TensorFlow by IBM via Edx: Fee, Duration, How to Apply

Quick Facts

particular	details
Medium of instructions English	Mode of learning Self study	Mode of Delivery Video and Text Based	Learning efforts 2-4 Hours Per Week

Course overview

A considerable amount of the world’s data is unstructured, including text, sound, images, etc. By joining the Deep Learning with TensorFlow certification course, you will learn how Deep Learning can be applied with TensorFlow to this kind of data and solve real-life problems. You will study the main functions, execution pipeline, basic concepts and operations of TensorFlow.

During the 5-week duration of the Deep Learning with TensorFlow online program, you will explore various kinds of Deep Architectures, like Autoencoders, Recurrent Networks, and Convolutional Networks. Also, you will learn how to implement TensorFlow for backpropagation to adjust the biases and weights while training the neural networks.

With the help of edX’s Deep Learning with TensorFlow course, you will learn how TensorFlow can be used in regression, minimizing error functions, curve fitting and classification. The course offers you free access to its contents for a limited duration and you can also get the option to avail of a professional certificate on completion after paying the prescribed fee.

Course and certificate fees

Deep Learning with TensorFlow fee structure :

Course option	Amount
Deep Learning with TensorFlow (course content audit)	Nil
Deep Learning with TensorFlow (content + certification)	$ 99

certificate availability

Yes

certificate providing authority

IBM

certificate fees

$99

Eligibility criteria

Before you enroll in Deep Learning with TensorFlow training, you must know Deep Learning and Machine Learning concepts. Also, you should be familiar with Jupyter and Python notebooks.

What you will learn

Statistical skills Knowledge of deep learning

Near the end of the Deep Learning with TensorFlow online course, you will gain insights into the following:

Usage of TensorFlow in minimization of error functions, regression, classification, and curve fitting
Applying TensorFlow for backpropagation
Basic TensorFlow concepts including execution pipelines, operations, and main functions
Different kinds of Deep Architecture, including Autoencoders, Recurrent Networks, and Convolutional Networks

The syllabus

Module 1: Advanced Keras Functionalities

Welcome to the Course
Video: Course Introduction
Reading: Course Overview
Advanced Keras Functional API
Video: Introduction to Advanced Keras
Video: Keras Functional API and Subclassing API
Lab: Implementing the Functional API in Keras
Practice Quiz: Advanced Keras Functional API
Custom Layers with Keras
Video: Creating Custom Layers in Keras
Video: Overview of TensorFlow 2.x
Lab: Creating Custom Layers and Models
Practice Quiz: Custom Layers with Keras
Advanced Keras Functionalities Summary
Reading: Summary and Highlights: Advanced Keras Functionalities
Reading: Glossary: Advanced Keras Functionalities
Graded Quiz: Advanced Keras Functionalities
Discussion Prompt: Meet and Greet [ ungraded]

Module 2: Advanced CNNs in Keras

Advanced CNNs and Data Augmentation
Video: Advanced CNNs in Keras
Video: Data Augmentation Techniques
Lab: Advanced Data Augmentation with Keras
Practice Quiz: Advanced CNNs and Data Augmentation
Transfer Learning on Pre-trained Models and Image Processing
Video: Transfer Learning in Keras
Video: Using Pre-trained Models
Lab: Transfer Learning Implementation
Video: TensorFlow for Image Processing
Reading:Tips for Transfer Learning Implementation
Practice Quiz: Transfer Learning on Pre-trained Models and Image Processing
Introducing Transpose Convolution
Video: Introducing Transpose Convolution
Lab: Practical Application of Transpose Convolution
Practice Quiz: Introducing Transpose Convolution
Advanced CNNs in Keras Summary
Reading: Summary and Highlights: Advanced CNNs in Keras
Reading: Glossary: Advanced CNNs in Keras
Graded Quiz: Advanced CNNs in Keras
Discussion Prompt: Data Augmentation and Transfer Learning

Module 3: Transformers in Keras

Transformers in Keras
Video: Introduction to Transformers in Keras
Video: Building Transformers for Sequential Data
Lab: Building Advanced Transformers
Practice Quiz: Transformers in Keras
Advanced Transformers and Sequential Data using TensorFlow
Video: Advanced Transformer Applications
Video: Transformers for Time Series Prediction
Video: TensorFlow for Sequential Data
Lab: Implementing Transformers for Text Generation
Practice Quiz: Advanced Transformers and Sequential Data using TensorFlow
Transformers in Keras Summary
Reading: Summary and Highlight: Transformers in Keras
Reading: Glossary: Transformers in Keras
Graded Quiz: Transformers in Keras
Discussion Prompt: Transforming Sequential Data with Transformers

Module 4: Unsupervised Learning and Generative Models in Keras

Unsupervised Learning, Autoencoders, and Diffusion Models
Video: Introduction to Unsupervised Learning in Keras
Video: Building Autoencoders in Keras
Lab: Building Autoencoders
Video: Diffusion Models
Lab: Implementing Diffusion Models
Practice Quiz: Unsupervised Learning, Autoencoders, and Diffusion Models
GANs and TensorFlow
Video: Generative Adversarial Networks (GANs)
Video: TensorFlow for Unsupervised Learning
Lab: Develop GANs using Keras

Module 5: Advanced Keras Techniques

Advanced Keras techniques and Custom Training Loops
Video: Advanced Keras Techniques
Video: Custom Training Loops in Keras
Lab: Custom Training Loops in Keras
Practice Quiz: Advanced Keras techniques and Custom Training Loops
Hyperparameter and Model Optimization
Video: Hyperparameter Tuning with Keras Tuner
Lab: Hyperparameter Tuning with Keras Tuner
Video: Model Optimization
Video: TensorFlow for Model Optimization
Practice Quiz: Hyperparameter and Model Optimization
Advanced Keras Techniques Summary
Reading: Summary and Highlight: Advanced Keras Techniques
Reading: Glossary: Advanced Keras Techniques
Graded Quiz: Advanced Keras Techniques and Custom Training Loops
Discussion Prompt: Custom Training Loops and Hyperparameter Optimization

Module 6: Introduction to Reinforcement Learning with Keras

Reinforcement Learning, Q-Learning, Q-Networks (DQNs)
Video: Introduction to Reinforcement Learning
ideo: Q-Learning with Keras
Lab: Implementing Q-Learning in Keras
Video: Deep Q-Networks (DQNs) with Keras
Lab: Building a Deep Q-Network with Keras
Practice Quiz: Reinforcement Learning, Q-Learning, Q-Networks (DQNs)
Module Summary
Reading: Summary and Highlight: Introduction to Reinforcement Learning with Keras
Reading: Glossary: Introduction to Reinforcement Learning with Keras
Graded Quiz: Introduction to Reinforcement Learning with Keras
Discussion Prompt: The Promise and Challenge of Reinforcement Learning

Module 7: Final Project and Assignment

Reading: Practice Project Overview: Fruit Classification Using Transfer Learning
Lab: Practice Project: Fruit Classification Using Transfer Learning
Reading: Final Project: Classify Waste Products Using Transfer Learning
Final Project: Classify Waste Products Using Transfer Learning
Project: Peer-graded Assignment: Classify Waste Products Using Transfer Learning

Course Wrap Up

Video: Course Wrap-up
Reading: Congratulations and Next Steps
Reading: Thanks from the Course Team

Admission details

Step 1 – Open the Deep Learning with TensorFlow course page.

Step 2 – Near this webpage’s top, you can choose the session for enrollment. Then hit the ‘Enroll now’ button below to reach the registration page.

Step 3 – You can sign up using your Facebook, Microsoft, Apple, or Google account. Alternatively, you can fill in your basic details and tap the ‘Create account’ button to register for an account.

Step 4 – A new page with a ‘Congratulations’ message will open. You should now be enrolled in the Deep Learning with TensorFlow programme by edX. You have the option to audit the course for free or buy the paid, verified track.

Filling the form

You don’t have to fill and submit an application form to get admission to the Deep Learning with TensorFlow online programme. Just visit the edX website and sign up to join the course. You need to enter your username, full name, country, new password and email ID to create a new account. You can even link your existing social accounts to sign in.

How it helps

The Deep Learning with TensorFlow course by edX follows a flexible learning approach. It is entirely self-paced so that you can learn the course modules at your own convenience. The lessons are delivered exclusively by IBM experts.

Also, you can opt for Deep Learning with TensorFlow certification. This official certificate will be signed by instructors and have IBM’s logo. This valid credential will be proof of your accomplishment and help you land better jobs.

Instructors

Mr Saeed Aghabozorgi
Senior Data Scientist
IBM

Ph.D

Mr Romeo Kienzler
Data Scientist
IBM

Other Masters

Ms Samaya Madhavan
Software Engineer
IBM

B.E /B.Tech, Other Masters

FAQs

Which organisation presents this course?

The Deep Learning with TensorFlow course is offered by IBM.

Who are the instructors for the Deep Learning with TensorFlow programme?

The course will be taught by expert instructors of IBM. Samaya Madhavan, Advisory Software Engineer; Romeo Kienzler, Chief Data Scientist and Saeed Aghabozorgi, Senior Data Scientist, will be your instructors.

What are the prerequisites to enrol?

You should have familiarity with Python and Jupyter notebooks. Moreover, you must have a fair understanding of Deep Learning and Machine Learning concepts.