Fill the below form to buy the course
Please enter a valid mobile number
*EMI / Pay Later options available on the payment page for selected credit/debit cards.

Artificial Intelligence with Deep Learning Certification

Build a career in the exciting field of AI with our Deep Learning Online Certification Course.

This training willl help you learn various aspects of AI like Deep Learning with Pytorch, Machine Learning, Artificial Neural Networks, Expert systems, Object Detection and Vernacular Language Signboard Translation as a Capstone Project.

You will get 13 certification, after the completion of individual module and 1 final certificate.This program will prepare you to solve real world problems using cutting edge technologies.

Key Features
  • Course taught by IIT Madras Professors who are subject matter experts in the field.
  • 100+ hours of self paced videos with Lifetime Access.
  • 12 Modules certification.
  • Globally Recognized Certificate from GUVI after successful completion
  • Dedicated Forum Support from the Instructors
  • 100% Online Learning
  • Access to community of over 5000 DL Students and Enthusiasts
  • Frequent Kaggle contests
  • 7 days Refund Policy
  • Basic knowledge of Python.
  • Time commitment of 4 hours a week.
  • Laptop / desktop with internet access.
Who Should Enroll in this course
  • IT Professionals
  • IT Consultants
  • IT Graduates & Freshers
  • Any Graduate with Programming Knowledge
Fee structure
Eligibility Students enrolled in schools/colleges without any prior work experience and faculty members of colleges and universities. Requisites Applicants must provide a valid details indicating their present enrolment in any recognised educational institution. Fee Structure 11800 1180 (You Save: 90% )
Eligibility Working professionals from companies and any other applicant with work-experience looking to upskill. Requisites Nil. Just apply directly. Fee Structure 11800 5900 (You Save: 50% )
About instructors
Mitesh M. Khapra is an Assistant Professor in the Department of Computer Science and Engineering at IIT Madras. He researches in the areas of Deep Learning, Multimodal Multilingual Processing, Dialog systems and Question Answering. He holds masters and Ph.D degrees from IIT Bombay. He has worked for over 4.5 years at IBM Research and published over 25 papers. He was a recipient of IBM PhD Fellowship and the Microsoft Rising Star Award. He is also a recipient of the Google Faculty Research Award, 2018.
Pratyush is an Assistant Professor at the Department of Computer Science and Engineering at IIT Madras since April 2018. He received his Bachelors and Masters of Technology in Electrical Engineering from IIT Bombay in 2009. He then completed his PhD in Computer Engineering from ETH Zurich in 2014. He then spent over 2.5 years at IBM Research, Bangalore and a few months consulting for machine learning and startups. His current research focus is on hardware-software co-design of deep learning systems. He has authored over 35 research papers and has applied for over 20 patents.
What is inside ?
Getting Started
This module serves as a refresher to the basics of Python programming and the mathematical concepts key to Machine Learning. You will also be introduced to Expert Systems, and how they were replaced with Machine Learning. We will use our 6-Jar framework to build a solid foundation for breaking all ML/DL models.
Primitive Neurons
This module introduces us to the building block of Artificial Neural Networks, the Artificial Neuron. You will learn about the McCulloch-Pitt's Neuron (MP Neuron) and the Perceptron and their influence on modern neuron design. You will learn how to apply the 6-Jar framework through the study of these neurons. At the end of the module, participants will enter their first Kaggle contest - The Mobile Phone Like/Dislike predictor.
Sigmoid Neuron
This module introduces a neuron capable of handling non-linearly separable data, the Sigmoid Neuron. You will be introduced to Learning algorithms, more specifically, the Gradient Descent update rule. The key concepts behind Probability Theory, Information Theory and Cross Entropy will be taught in this module. The next set of Kaggle Contests will be introduced - The Binary Text/No-Text Classifier.
Feedforward Neural Networks
This module teaches you about the Universal Approximation Theorem. With the intuition gained on the representation power of function, you will learn about Feedforward Neural Networks, and their ability to handle complexities in data and tasks. You will compare the performance of Sigmoid Neurons with FFNs by programming them in Python.
Training Feedforward Neural Networks
This module is an in-depth tutorial on the learning mechanism for all Neural Networks, namely Backpropagation. You will gain intuition on Backpropagation through 2 levels (math-light and math-heavy) and solidify your understanding by coding backpropagation algorithms in Python.
Optimization Algorithms
This module covers the different optimization algorithms used in deep learning including the different variants of Gradient Descent, Adagrad, RMSProp and Adam. You will also learn about different activation functions like sigmoid, tanh, ReLu etc as well as Initialization methods. Finally, Regularization concepts will be taught and intuition for all the aforementioned concepts will be reinforced by programming them in Python.
Introduction to Pytorch
This module is the introduction to the PyTorch framework for deep learning. You will get hands-on experience in programming with PyTorch by building Feedforward Neural Networks.
Convolutional Neural Networks
This module introduces the cornerstone of vision based deep learning models, The Convolutional Neural Network. You will gain intuition on how the convolution operation works and then apply it to neural networks to build your very first CNN.
Deep Convolutional Neural Networks
This module talks about the Imagenet classification challenge. You will learn about the most popoular CNN architectures, the best performers on the Imagenet challenge over the first half of this decade (2010-2015). You will also learn how to implement these architectures in PyTorch. Concepts such as Batch Normalization, Dropout, Hyperparameter Tuning etc. as well as their implementation will also be covered.
Sequence Models
This module introduces the concept of Sequece Based Models. You will learn about Recurrent Neural Networks, Vanishing and Exploding Gradients, LSTMs and GRUs, Batching Sequence models and how to code them in PyTorch.
Encoder Decoder Models
This module covers Encoder-Decoder models and their application in language modelling. It will also cover Attention Mechanism. Finally, you will code the aforementioned concepts in PyTorch.
Introduction to Object Detection
This module introduces you the Object Detection and typical its typical pipelines. You will learn about Region-based CNNs (RCNNs) and You Only Look Once (YOLO) models for object detection.
Capstone Project
This module is a culmination of all the learning over the previous 12 modules to perform the open-ended project, Vernacular Language Signboard Translation.
For futher queries, Write a mail to [email protected]
Sample certificate
Our learners

"This course is the best as it focuses both on the theory and hands on.This course introduced me to Kaggle competitions and I got addicted to it.I feel more confident that I can contribute to real world projects involving deep learning after taking this course."

"Learned a lot from this course. Before starting this course, I have no knowledge of deep learning but after learning this course I am pretty confident."

"This course can turn you into a deep learning enthusiast if you have the urge to learn something new (even if you don't know anything about deep learning at all)."

About Deep Learning
Deep learning refers to a set of techniques by which we can achieve varying degrees of artificial intelligence by mimicking the working of a human brain. Deep learning is a subset of Machine Learning techniques that aim to achieve Artificial Intelligence.The distinguishing feature of Deep Learning is its use of various Artificial Neural Networks, that imitate the human brain. Just as in the brain, Artificial Neural Networks or ANNs also consist of neurons and synapses between them. Deep Learning vs Machine Learning: In traditional Machine Learning, the data must be broken down into individual features. These hand-crafted features are fed into the model and we get a prediction as an output. However, hand-crafting features is a time-consuming process that involves a lot of statistical knowledge and expertise in data science. With the advent of Deep Learning and multi-layered Artificial Neural Networks, feature selection can now be handled by the model itself. By feeding it numerical representation of raw data (Images, Video, Audio etc), the multi-layered architecture allows for the model to determine the highest-contributing features and uses them to make successful predictions, without any human crafted features. This drastically shortened project timelines and human intervention in the preliminary stages. A small caveat is that DL models required larger volumes of data to train than traditional ML models. Advantages of studying Deep Learning: Deep learning is a buzz-word, synonymous with cutting edge Artificial Intelligence. Whether it’s Waymo’s self driving car, OpenAI’s DoTA playing AI or digital smart assistants like Siri or Alexa, the impact that deep learning has had on modern day technology is significant. Let us discuss some of the advantages studying deep learning.
  • Data-Driven Everything - Deep Learning can be applied to ANY domain at some capacity, so long as there are volumes of data generated to train the models.
  • Highly Accessible - Advancements in software, hardware and the open-source community of Deep Learning Practitioners have made DL the most accessible it’s ever been since its inception.
  • Math and Python - As this point is titled, high-school math and basic knowledge of Python syntax is all you need to begin your journey as a deep learning practitioner.
  • 0 to 60 in 0.5 - With around 5-8 hours of study per week and around 6 months of time, learners can progress rapidly from novice to intermediate/adept levels.
Deep Learning Career Opportunities: Projects @ IT/ITeS Companies: For those looking to transition into DL/ML projects at IT companies, familiarity of programming, application and mathematics behind deep learning will be suitable. DL products @ startups: For those looking to join startups focused on DL products, a working level of proficiency in programming, mathematics and application of DL techniques would be required Research @ universities, research labs: For those looking to enter the research field, expert understanding of Deep-Learning, its underlying concepts and its practical application are required.
Why study through GUVI?
Guvi is an IIT-M , IIM-A incubated company located at IITM Research Park, Chennai. We help students master any programming skills so that they can learn and effectively practice the acquired knowledge and skills necessary to thrive in their career. Our feature includes practicing exercises, instructional videos, and a personalized learning dashboard that empowers learners to study at their own pace.
Partner with us
Universities and Colleges If you are an educational institution and would like to adopt our courses for your curriculum, we are very happy to support you. We can bulk enrol your students and provide certification for them to receive appropriate credit at your institution.
Foundations and NGOs If you are a foundation or an NGO and find synergy with our goal of affordable AI education, you can offer support for curriculum design and awards for top- performing students.
Corporates and Startups If you would like to train several of your employees on AI, please write to us to receive customized reports on how they perform. You can also partner with us on the DL garage by defining problem statements and awarding student grants.
Frequently Asked Questions
How is this different from other courses?
The focus of the courses is primarily on combining theoretical knowledge with hands-on experience. Further, the emphasis is to go from limited pre-requisites to solving a challenging problems. Finally, we hope to build a community around PadhAI by continuing to engage with you after the course through the DL garage, subsequent courses, and also through our startup One Fourth Labs which will build solutions on Deep Learning.
Will I get a certificate on completing a course?
Yes, upon successful completion, you will get a certificate from GUVI. This certificate will be accessible to you.
What are the pre-requisites?
The primary pre-requisite is a working knowledge of Python. We do not expect you to be familiar with AI or related topics. Mathematical understanding equivalent to 12th standard syllabus would be sufficient. However, the course requires a time commitment of 4 hours per week.
How can I ask my doubts?
We will have discussion forums where you can discuss the topics covered and ask doubts. Your peers or our Teaching assistants will answer the questions. Additionally, there will periodical video calls once a fortnight where instructors will answer questions.
An IIT-M & IIM-A Incubated Company


Artificial Intelligence

Combo Pack

Learn Python, ML and DL
at a discounted price

View details