Self-Paced Online




IIT Roorkee




About the Course

Have you ever wondered how self-driving cars are running on roads or how Netflix recommends the movies which you may like or how Amazon recommends you products or how Google search gives you such an accurate results or how speech recognition in your smartphone works or how the world champion was beaten at the game of Go?

Deep learning is behind these innovations. In the recent times, it has been proven that machine learning and deep learning approach to solving a problem gives far better accuracy than other approaches. This has led to a Tsunami in the area of Machine Learning.

Most of the domains that were considered specializations are now being merged into Deep learning. This has happened because of the following:

  • Better research and algorithms
  • Better computing resources
  • Distributed computing infrastructures
  • Availablity of Big Data

Every domain of computing such as data analysis, software engineering, and artificial intelligence is going to be impacted by Deep learning. Therefore, every engineer, researcher, manager or scientist would be expected to know Machine Learning.

So naturally, you are excited about Machine learning and would love to dive into it. This specialization is designed for those who want to gain hands-on experience in solving real-life problems using deep learning. After finishing this specialization, you will find creative ways to apply your learnings to your work.

Program Highlights

  • Certificate of Completion by IIT Roorkee

  • 80+ Hours of Online Training

  • Work on about 12+ projects to get hands-on experience

  • Timely Doubt Resolution

  • Best In Class Curriculum

  • Cloud Lab Access


What is the certificate like?

  • Why IIT Roorkee?

    IIT Roorkee is ranked first among all the IITs AND 20th position globally in citations per faculty. Established in 1847, it's one of the oldest technical institutions in Asia. IIT Roorkee fosters a very strong entrepreneurial culture. Some of their alumni are highly successful as entrepreneurs in the new age digital economy.

  • Why Cloudxlab?

    CloudxLab (CxL) has been a pioneer in the edtech space for the past few years. Founded in 2015 by Sandeep Giri, an alumnus of IIT Roorkee, CxL has successfully transformed 1,000's of students' careers by offering world-class certification courses in big data, machine learning and artificial intelligence.

    Some of the unique features of CxL are an exclusive gamified learning environment through the lab (read as CloudxLab), highest rated faculty, excellent student support and more.

Hands-on Learning

hands-on lab
  • Gamified Learning Platform

  • Auto-assessment Tests

  • No Installation Required

Mentors / Faculty

Instructor Raksha Sharma

Raksha Sharma

Faculty CSE Dept

IIT Roorkee

Instructor Gaurav Dixit

Gaurav Dixit

Faculty DoMS Dept

IIT Roorkee

Instructor Sandeep Giri

Sandeep Giri

Founder at CloudxLab

Past: Amazon, InMobi, D.E.Shaw

Instructor Abhinav Singh

Abhinav Singh

Co-Founder at CloudxLab

Past: Byjus

Instructor Praveen

Praveen Pavithran

Co-Founder at Yatis

Past: YourCabs, Cypress Semiconductor


Hours of Online Training
Days of Lab Access
1. Linux for Data Science
2. Getting Started with Git
3. Python Foundations
4. Machine Learning Prerequisites(Including Numpy, Pandas and Linear Algebra)
5. Getting Started with SQL
6. Statistics Foundations
4. Introduction to Machine Learning and Deep Learning
In this topic, we will cover concepts like different types of Machine Learning algorithms (Supervised, Unsupervised, Reinforcement) and challenges in Machine Learning. We will see examples of solving the problems using the traditional approach and why Machine Learning algorithms give far better accuracy than the traditional approach. This topic will give you a brief introduction to both Machine Learning and Deep Learning world.
5. Data Preprocessing, Regression - Build end-to-end Machine Learning Project
We will start the course by learning concepts in Machine Learning. In this topic, we will build a machine learning model to predict housing pricing in California. By the end of this project, you will understand how to build machine learning pipelines to build a model. We will also cover concepts like data cleaning, preparing data for machine learning algorithms, exploring many different models, short-list the best one and fine-tuning the selected model
6. Classification
In this topic, we will train a model on the MNIST dataset to recognize handwritten digits. We will also learn various performance measures in classification like Confusion Matrix, Precision and Recall, and ROC Curve.
7. Machine Learning Algorithms
In this topic, we will learn various Machine Learning algorithms and concepts like Unsupervised Learning, Ensemble Learning, and Dimensionality Reduction
8. Introduction to Artifical Neural Networks with Keras
We will start the Deep Learning course with Artificial Neural Networks. We will learn about biological neurons, multilayer perceptrons, and back-propagation. We will implement a multilayer perceptron using Keras and visualize the runs and graphs using Tensorboard
9. Training Deep Neural Networks
In this topic, we will learn various challenges deep neural networks face while training like vanishing and exploding gradients. We will learn various techniques to solve these problems like reusing pre-trained layers, using faster optimizers and avoiding overfitting by regularization.
10. Custom Models and Training with TensorFlow
In this topic, we will dive deeper into TensorFlow and its lower level Python API. These lower-level Python APIs are useful when we need extra control like writing custom loss function, layers and many more.
11. Loading and Preprocessing Data with TensorFlow
Deep Learning systems are usually trained on very large datasets that may not fit in the RAM. In this topic, we will learn TensorFlow's Data API which helps in ingesting dataset and preprocessing it efficiently.
12. Deep Computer Vision using Convolutional Neural Network
In this topic, we will learn how Convolutional Neural Networks - CNNs achieve superhuman performance on complex visual tasks. Today CNNs power image search services, self-driving cars, automatic video classification systems and more. We will learn CNNs basic building blocks and how to implement them using TensorFlow and Keras
13. Processing Sequences Using RNNs and CNNs
Predicting the future is something we do all the time like predicting stock prices. In this topic, we will learn how Recurrent Neural Networks - RNN predict the future, the problem they face like limited short-term memory and solutions to these problems - LSTM (Long Short-Term Memory) and GRU cells
14. Natural Language Processing Concepts and RNNs
Using Natural Language Processing we build systems that can read and write natural language. In this topic, we will learn different NLP techniques and generate Shakespearean text using a Character RNN.
15. Representation Learning & Generative Learning Using autoencoders and GANs
Autoencoders are artificial neural networks capable of learning dense representations of input data without any supervision. For example, we could train an autoencoder on pictures of faces and it can then generate new faces. In this topic, we will learn different types of autoencoders and generative models.
16. Reinforcement Learning
Reinforcement Learning is one of the most exciting fields of Machine Learning. Using Reinforcement Learning AlphaGo(system) defeated the world champion at the game of Go. Reinforcement Learning is an area of Machine Learning aimed at creating agents capable of taking actions in an environment in a way that maximizes rewards over time. In this topic, we will learn various concepts in Reinforcement Learning and experiment with OpenAI Gym.


Apply Now

Certification Guideline

    1. Complete at least 60% of the topics of the course along with any 3 mandatory(non optional) projects. All the above requirements need to be met within 180 days from the course enrollment date to be eligible for the certificate.

Program Fee


  • 80+ Hours of Online Self-Paced Training
  • 180 Days of Online Lab Access
  • 24*7 Support
  • Certificate from IIT Roorkee
Enroll Now »


Frequently Asked Questions

Do I need to install any software before starting this course?

No, we will provide you with the access to our online lab and BootML so that you do not have to install anything on your local machine

Can I expect any placement support?

Yes, we do offer placement assistance that includes career guidance, resume building tips and mock interviews. Each participant will receive staunch support from the industry mentors, who also direct you through various placement opportunities within the industry. Above all, we are partnered with leading MNC’s that offer placement opportunities to our participants.

Can I get a certificate for the projects completed?

We have created a set of Guided Projects on our platform. You may complete these guided projects and earn the certificate for free. Check it out here

What is the certification process?

In this course, you will work on real-world projects. You will receive a problem statement along with a data-set to work on CloudxLab. Once you are done with the projects (it will be reviewed by an expert), you will be awarded a certificate which you can share on LinkedIn.

Is there any prerequisite of this course?

You should have the knowledge of about Machine Learning to get the concepts of this course.

What is the validity of course material?

We understand that you might need course material for a longer duration to make most out of your subscription. You will get lifetime access to the course material so that you can refer to the course material anytime.

What is your refund policy?

If you are unhappy with the product for any reason, let us know within 7 days of purchasing or upgrading your account, and we'll cancel your account and issue a full refund. Please contact us at to request a refund within the stipulated time. We will be sorry to see you go though!