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
Over the past few years, Deep Learning has received a lot of attention due to its wide-ranging applications in data analytics, natural language processing, and computer vision. Many professionals who are well versed in deep learning technologies have been employed by leading companies like Google, IBM, Facebook, Microsoft, and Twitter. In this Deep learning – IIT Ropar online training, you will get familiar with the building blocks of deep learning algorithms and solutions.
The Deep Learning – IIT Ropar course syllabus places a particular emphasis on neural network topics like attention mechanisms, convolutional neural networks, feed-forward neural networks, and recurrent neural networks. Various deep learning optimisation algorithms such as Nesterov Accelerated Gradient Descent, Gradient descent, Adam, AdaGrad, and RMSProp are also covered. Learning these algorithms and methods will help effectively train deep neural networks.
After completing all the lectures and assignments of the Deep Learning – IIT Ropar programme, you’ll have a robust grasp of deep learning architectures, which you can employ to carry out various computer vision and Natural Language Processing tasks. You can also test your understanding by applying for the final proctored exam. Passing this test will also grant you a certificate by Swayam, which can be used to display your skills and get lucrative jobs.
The Highlights
- Offered by IIT Ropar
- Undergraduate/Postgraduate level difficulty
- 12-week, scheduled training programme
- Weekly assignments
- Paid proctored exam
- Expert faculty from IIT Ropar
- E-certificate available
Important dates
Course Commencement Date
Start Date : 20 Jan, 2025
End Date : 11 Apr, 2025
Enrollment Date
End Date : 27 Jan, 2025
Other
End Date : 14 Feb, 2025
Certificate Exam Date
Start Date : 03 May, 2025
Programme Offerings
- E-certificate available
- 12-week
- scheduled training programme
- Expert faculty from IIT Ropar
- Weekly Assignments
- Paid proctored exam
- Undergraduate/Postgraduate level difficulty
- Offered by IIT Ropar.
Courses and Certificate Fees
| Fees Informations | Certificate Availability | Certificate Providing Authority |
|---|---|---|
| INR 1000 | yes | IIT Ropar (IIT-RPR) |
An examination fee is payable if you wish to appear for the proctored test. Accessing the course material is free.
Deep Learning – IIT Ropar programme fee structure
Course | Fees |
Deep Learning – IIT Ropar | FREE |
Deep Learning – IIT Ropar – Certificate + exam | Rs. 1,000 |
Eligibility Criteria
It is recommended that you take an introductory machine learning course before enrolling in Deep Learning - IIT Ropar certification course. Also, having a working knowledge of probability theory and linear algebra will easily navigate the course.
Certificate Qualifying Details
The certificate is provided at the end of the course, provided that you have submitted all the assignments and passed the final proctored exam.
What you will learn
By the end of the Deep Learning – IIT Ropar online training, you will have a firm grasp of the topics listed below:
- Regularisation and its types
- Gradient descent and its types
- Normalisation and its types
- Autoencoders
- Convolutional neural networks and their types
- Attention mechanism
- Perceptron networks, neuron, and multi-layer perceptrons
- Deep learning algorithms like gradient descent, backpropagation algorithm, and feed-forward algorithm
Who it is for
The Deep Learning - IIT Ropar certification course isn’t catered towards a specific demographic and can be accessed by anyone interested in learning the deep learning fundamentals.
Admission Details
- https://onlinecourses.nptel.ac.in/noc25_cs21/preview: Use this link to access the Deep Learning – IIT Ropar webpage.
- Upon landing, click the ‘Join Now’ option on the top right. You can also go through the details before joining.
- After clicking the ‘Join Now’ option, you will be redirected to the Register/Login page. Create an account by filling a form or sign in if you already have an account.
- After logging in, you’ll be provided access to all course materials. You can start learning right away.
Application Details
There’s no dedicated application form that needs to be submitted to enrol in Deep Learning – IIT Ropar online programme. All you have to do is log in, and you will be provided access to all course material and assignments. However, a small form needs to be filled if you don’t have a Swayam account. The form consists of necessary details regarding your contact information, education, and work experience.
The Syllabus
- History of Deep Learning(Partial)
- Deep Learning Success Stories
- McCulloch Pitts Neuron
- Thresholding Logic
- Perceptrons
- Perceptron Learning Algorithm
- Multilayer Perceptrons (MLPs)
- Representation Power of MLPs
- Sigmoid Neurons
- Gradient Descent
- Feedforward Neural Networks
- Representation Power of Feedforward Neural Networks
- FeedForward Neural Networks
- Backpropagation
- Gradient Descent (GD)
- Momentum Based GD
- Nesterov Accelerated GD
- Stochastic GD
- AdaGrad
- RMSProp
- Adam
- Eigenvalues and eigenvectors
- Eigenvalue Decomposition
- Basis
- Principal Component Analysis and its interpretations
- Singular Value Decomposition
- Autoencoders and relation to PCA
- Regularization in autoencoders
- Denoising autoencoders
- Sparse autoencoders
- Contractive autoencoders
- Regularization: Bias Variance Tradeoff
- L2 regularization
- Early stopping
- Dataset augmentation
- Parameter sharing and tying
- Injecting noise at input
- Ensemble methods
- Dropout
- Greedy Layerwise Pre-training
- Better activation functions
- Better weight initialization methods
- Batch Normalization
- Learning Vectorial Representations Of Words
- Convolutional Neural Networks
- LeNet
- AlexNet
- ZF-Net
- VGGNet
- GoogLeNet
- ResNet
- Visualizing Convolutional Neural Networks
- Guided Backpropagation
- Deep Dream
- Deep Art
- Fooling Convolutional Neural Networks
- Recurrent Neural Networks
- Backpropagation through time (BPTT)
- Vanishing and Exploding Gradients
- Truncated BPTT
- GRU
- LSTMs
- Encoder Decoder Models
- Attention Mechanism
- Attention over images
Evaluation process
A minimum required criterion, specified by Swayam, must be followed if you wish to earn the certificate. The certificate is granted depending upon the marks you have procured in assignments as well as the final exam. Best eight assignments are considered for evaluation, in which you must have obtained at least 40% marks. Moreover, you also have to get a minimum of 40% marks in the final assessment.
Instructors
IIT Ropar (IIT-RPR) Frequently Asked Questions (FAQ's)
As the course is 12-weeks long, it’s divided into 12 modules.
You must submit 12 assignments by the end of the course.
No, your final grade will be based on the average of the best eight assignments out of 12.
Yes, the course is developed by Swayam and IIT Ropar and is delivered by Swayam.
The video lectures are mentored by Prof. Sudarshan Iyengar, an assistant professor at IIT Ropar.