Deep Learning Course | IIT Kharagpur | Prof. Prabir Biswas | AI & Computer Vision
Course Details
| Exam Registration | 2288 |
|---|---|
| Course Status | Ongoing |
| Course Type | Elective |
| Language | English |
| Duration | 12 weeks |
| Categories | Electrical, Electronics and Communications 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 | 25 Apr 2026 IST |
| NCrF Level | 4.5 — 8.0 |
Unlock the Power of Artificial Intelligence with a Structured Deep Learning Journey
In today's data-driven world, the ability to interpret vast amounts of image, video, and text data is paramount. Deep Learning has emerged as the revolutionary force behind major advancements in Artificial Intelligence (AI), Computer Vision, and Natural Language Processing (NLP). This 12-week course, meticulously designed and taught by Prof. Prabir Kumar Biswas of IIT Kharagpur, provides a rigorous foundation and cutting-edge knowledge to master this transformative technology.
About the Instructor: Learn from an Esteemed Expert
Gain insights directly from a leading authority in the field. Prof. Prabir Kumar Biswas is a distinguished faculty member and the Head of the Department of Electronics and Electrical Communication Engineering at IIT Kharagpur.
- Qualifications: B.Tech (Hons), M.Tech, and Ph.D. from IIT Kharagpur.
- Industry & Research Acumen: Former Deputy Engineer at Bharat Electronics Ltd. and an Alexander von Humboldt Research Fellow at the University of Kaiserslautern, Germany.
- Proven Expertise: Author of 100+ research publications, holder of 7 international patents, and a Senior Member of IEEE. His research spans Image Processing, Pattern Recognition, Computer Vision, and Video Compression.
Who Should Enroll in This Deep Learning Course?
This course is strategically crafted for students and professionals looking to build or advance their career in AI.
- Intended Audience: Undergraduate and Postgraduate students in Electronics & Communication Engineering, Computer Science, Electrical Engineering, Data Science, and Robotics.
- Prerequisites: A foundational knowledge of Linear Algebra, Digital Signal Processing (DSP), and Partial Differential Equations (PDE) will be beneficial.
- Industry Support: The curriculum is highly valued by top-tier companies including Google, Adobe, TCS, and DRDO, ensuring the skills you learn are directly applicable in the industry.
Course Overview: From Foundational Concepts to Advanced Architectures
This comprehensive program takes you on a structured learning path, starting with core machine learning principles and progressing to the most advanced deep learning models used in industry and research today.
Detailed 12-Week Course Layout
| Week | Topics Covered |
|---|---|
| Week 1 | Introduction to Deep Learning, Bayesian Learning, Decision Surfaces |
| Week 2 | Linear Classifiers, Linear Machines with Hinge Loss |
| Week 3 | Optimization Techniques: Gradient Descent, Batch Optimization |
| Week 4 | Introduction to Neural Networks, Multilayer Perceptron, Backpropagation |
| Week 5 | Unsupervised Learning with Deep Networks: Autoencoders |
| Week 6 | Convolutional Neural Networks (CNN): Building Blocks, Transfer Learning |
| Week 7 | Advanced Optimizers: Momentum, RMSProp, Adam |
| Week 8 | Effective Training: Early Stopping, Dropout, Batch/Instance/Group Normalization |
| Week 9 | Recent Architectures: Residual Networks (ResNet), Skip Connections, Fully Connected CNN |
| Week 10 | Classical Supervised Tasks: Image Denoising, Semantic Segmentation, Object Detection |
| Week 11 | Sequential Data Modeling: LSTM Networks |
| Week 12 | Generative Modeling: Variational Autoencoders (VAE), Generative Adversarial Networks (GANs) |
Key Learning Outcomes
Upon successful completion of this course, you will be able to:
- Understand the mathematical and conceptual foundations of Machine Learning and Deep Learning.
- Design, implement, and train Multilayer Perceptrons (MLP) and Convolutional Neural Networks (CNN).
- Apply advanced optimization and regularization techniques to build robust models.
- Implement state-of-the-art architectures like ResNet for complex computer vision tasks.
- Work with sequential data using LSTM networks.
- Understand and build generative models using Autoencoders and GANs.
- Solve real-world problems in image analysis, object detection, and more.
Recommended Textbooks
- Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville (MIT Press).
- Pattern Classification by Richard O. Duda, Peter E. Hart, and David G. Stork (John Wiley & Sons).
Embark on your deep learning expertise with guidance from an IIT Kharagpur pioneer. This course is your gateway to mastering the algorithms that are shaping the future of technology.
Enroll Now →