Deep Learning Course by IIT Ropar & IIT Madras | AI & ML Certification
Course Details
| Exam Registration | 4770 |
|---|---|
| Course Status | Ongoing |
| Course Type | Elective |
| Language | English |
| Duration | 12 weeks |
| Categories | Computer Science and Engineering, Artificial Intelligence, Data Science, Robotics |
| Credit Points | 3 |
| Level | Undergraduate/Postgraduate |
| Start Date | 19 Jan 2026 |
| End Date | 10 Apr 2026 |
| Enrollment Ends | 02 Feb 2026 |
| Exam Registration Ends | 20 Feb 2026 |
| Exam Date | 17 Apr 2026 IST |
| NCrF Level | 4.5 — 8.0 |
Master the Future of AI with a Premier Deep Learning Course from IIT Ropar & IIT Madras
In the rapidly evolving landscape of technology, Deep Learning stands as a cornerstone of modern Artificial Intelligence. From powering sophisticated image recognition systems to enabling natural human-computer conversations, its applications are revolutionizing industries globally. Recognizing the critical need for skilled professionals in this domain, Indian Institute of Technology Ropar, in collaboration with IIT Madras, offers a comprehensive 12-week course designed to build a strong foundational and practical understanding of Deep Learning architectures and algorithms.
About the Course: Your Gateway to Advanced AI
This meticulously structured course delves into the core building blocks that have enabled tech giants like Google, Microsoft, IBM, and Facebook to solve complex problems in Computer Vision and Natural Language Processing (NLP). Over 12 intensive weeks, participants will transition from understanding the fundamental perceptron to exploring cutting-edge attention mechanisms. The curriculum is designed to equip students with the knowledge to design and implement deep architectures for real-world AI tasks.
Learn from Distinguished Faculty and Industry Experts
The course brings together the academic excellence and industry experience of two renowned professors:
- Prof. Mitesh M. Khapra (IIT Madras): An Assistant Professor in CSE at IIT Madras and a recipient of the Google Faculty Research Award (2017). With a Ph.D. from IIT Bombay and prior experience as a Researcher at IBM India, Prof. Khapra brings rich expertise in Deep Learning, Multimodal Learning, Dialog Systems, and Question Answering. His work is regularly published in top-tier computational linguistics and machine learning conferences.
- Prof. Sudarshan Iyengar (IIT Ropar): An Associate Professor in CSE at IIT Ropar with a Ph.D. from IISc. An exemplary educator, Prof. Iyengar has delivered over 350 popular science talks and more than 100 hours of online lectures, impacting lakhs of students. His research interests span Data Sciences, Social Computing, Social Networks, and Collective Intelligence.
Detailed 12-Week Course Curriculum
The course is divided into a progressive weekly schedule, ensuring a logical flow from basics to advanced concepts:
| Week | Topics Covered |
|---|---|
| Week 1-2 | History of DL, Perceptrons, Multilayer Perceptrons (MLPs), Sigmoid Neurons, Gradient Descent, Feedforward Neural Networks. |
| Week 3-4 | Backpropagation, Advanced Optimization Algorithms (Momentum GD, Nesterov GD, Adam, AdaGrad, RMSProp), Linear Algebra Fundamentals. |
| Week 5-6 | Dimensionality Reduction: PCA, SVD. Introduction to Autoencoders: Denoising, Sparse, Contractive. |
| Week 7-8 | Essential Regularization Techniques (L2, Dropout, Early Stopping), Advanced Training: Greedy Layerwise Pre-training, Batch Normalization, Better Initialization. |
| Week 9 | Learning Vectorial Representations of Words (Word Embeddings). |
| Week 10 | Convolutional Neural Networks (CNNs): Architectures from LeNet to ResNet, Visualization, Deep Dream, Adversarial Examples. |
| Week 11 | Recurrent Neural Networks (RNNs): Backpropagation Through Time (BPTT), GRUs, Long Short-Term Memory Networks (LSTMs). |
| Week 12 | Advanced Architectures: Encoder-Decoder Models and the pivotal Attention Mechanism. |
Who Should Enroll?
- Intended Audience: Undergraduate and Postgraduate students, working professionals, and any learner passionate about AI and Machine Learning.
- Prerequisites: A working knowledge of Linear Algebra and Probability Theory is required. Prior exposure to a foundational Machine Learning course is highly beneficial for maximizing learning outcomes.
Key Learning Outcomes
Upon successful completion, participants will:
- Gain a thorough understanding of core Deep Learning architectures: Feedforward Networks, CNNs, RNNs, and Autoencoders.
- Master training techniques and optimization algorithms like Gradient Descent variants, Adam, and RMSProp.
- Understand critical concepts for model robustness, including regularization and batch normalization.
- Build a solid foundation for working on advanced Computer Vision and Natural Language Processing tasks.
- Learn directly from faculty associated with premier IITs and gain insights from their industry and research experience.
Recommended Textbook
Students are encouraged to refer to the seminal textbook: "Deep Learning" by Ian Goodfellow, Yoshua Bengio, and Aaron Courville (MIT Press). It serves as an excellent companion to the course material. The book is available online at http://www.deeplearningbook.org.
Embark on your journey to becoming an AI expert with this authoritative course from IIT Ropar and IIT Madras. Enroll today to decode the complexities of Deep Learning and position yourself at the forefront of technological innovation.
Enroll Now →