Deep Learning for Computer Vision
Gain the skills and knowledge needed for deep learning for computer vision with Deep Learning for Computer Vision certification by NPTEL
Online
12 WeeksQuick Facts
| Medium Of Instructions | Mode Of Learning | Mode Of Delivery |
|---|---|---|
| English | Self Study | Video and Text Based |
Course Overview
The Deep Learning for Computer Vision certification course offers a comprehensive curriculum that covers the core aspects of deep learning for computer vision. The duration of this certification course is 12 weeks and completion of a basic course in Machine Learning course, and basic knowledge in probability, linear algebra, calculus, and Python are the prerequisites for this course.
The students will explore the traditional computer vision topics before they learn about the deep learning methods for computer vision. The Deep Learning for Computer Vision certification by NPTEL provides the basics as well as the latest advancement skills and knowledge in the field of computer vision and machine learning.
Also Read: Online Machine Learning Courses & Certifications
The Highlights
- 12 Weeks to Complete
- Certification from IIT, NPTEL
- For Senior UG/PG Students
- Completion Certification
Programme Offerings
- live sessions
- Hands-on Learning
- Books
- videos
- Transcripts
- assignments.
Courses and Certificate Fees
| Certificate Availability | Certificate Providing Authority |
|---|---|
| yes | IIT Madras (IITM) |
Eligibility Criteria
Academic Qualifications
Deep Learning for Computer Vision certification course requires certain prerequisites such as:
- Candidates must be Senior undergraduate students or post-graduate students.
- Students must have done a Basic course in Machine Learning.
- Deep Learning, or exposure to topics in Neural Networks (recommended, but not mandatory).
- Basic knowledge of probability, linear algebra, and calculus.
- Experience in Programming languages, preferably in Python.
What you will learn
After completing the Deep Learning for Computer Vision certification syllabus, the students will gain in-depth insights into Computer Vision and deep learning methods and techniques used by industry experts. They will also learn visual matching, Convolutional Neural Networks (CNNs), and CNNs for recognition, verification, detection, and segmentation.
Students will also gain proficiency in applying the methods and principles learned from the course in the real world. They will also learn the attention models, deep generative models, variants and applications of generative models in vision, and the recent trends as well after completing the Deep Learning for Computer Vision training.
Who it is for
The Deep Learning for Computer Vision online course is designed for aspiring students who are looking to enhance their skills and knowledge. This course can also be beneficial for:
Admission Details
To join the Deep Learning for Computer Vision classes, follow these steps:
Step 1: Click the link below:
https://nptel.ac.in/courses/106106224
Step 2: Login In by creating a separate account or Log In with Microsoft or Google Account.
Step 3: Submit the form by filling in the details mentioned in the form and joining the course.
The Syllabus
Introduction and Overview
- Course Overview and Motivation; History of Computer Vision; Image Representation; Linear Filtering, Correlation, Convolution; Image in Frequency Domain
- (Optional) Image Formation; Image Sampling
Visual Features and Representations
- Edge Detection; From Edges to Blobs and Corners; Scale Space, Image Pyramids and Filter Bank; SIFT and Variants; Other Feature Spaces
- (Optional) Image Segmentation, Human Visual System
Visual Matching
- Feature Matching; From Points to Images: Bag-of-Words and VLAD Representations; Image Descriptor Matching; From Traditional Vision to Deep Learning
- (Optional) Hough Transform; Pyramid Matching
Deep Learning Review
- Neural Networks: A Review; Feedforward Neural Networks and Backpropagation; Gradient Descent and Variants; Regularization in Neural Networks; Improving Training of Neural Networks
Convolutional Neural Networks (CNNs)
- Convolutional Neural Networks: An Introduction; Backpropagation in CNNs; Evolution of CNN Architectures for Image Classification; Recent CNN Architectures; Finetuning in CNNs
Visualization and Understanding CNNs
- Explaining CNNs: Visualization Methods; Early Methods (Visualization of Kernels; Backpropto-image/Deconvolution Methods); Class Attribution Map Methods (CAM,Grad-CAM, GradCAM++, etc); Going Beyond Explaining CNNs
- (Optional) Explaining CNNs: Recent Methods
CNNs for Recognition, Verification, Detection, Segmentation
- CNNs for Object Detection; CNNs for Segmentation; CNNs for Human Understanding: Faces
- (Optional) CNNs for Human Understanding: Human Pose and Crowd; CNNs for Other Image Tasks
Recurrent Neural Networks (RNNs)
- Recurrent Neural Networks: Introduction; Backpropagation in RNNs; LSTMs and GRUs; Video
- Understanding using CNNs and RNNs
Attention Models
- Attention in Vision Models: An Introduction; Vision and Language: Image Captioning; SelfAttention and Transformers
- (Optional) Beyond Captioning: Visual QA, Visual Dialog; Other Attention Models
Deep Generative Models
- Deep Generative Models: An Introduction; Generative Adversarial Networks; Variational Autoencoders; Combining VAEs and GANs
- (Optional) Beyond VAEs and GANs: Other Deep Generative Models
Variants and Applications of Generative Models in Vision
- GAN Improvements; Deep Generative Models across Multiple Domains; Deep Generative Models: Image Application
- (Optional) VAEs and Disentanglement; Deep Generative Models: Video Applications
Recent Trends
- Few-shot and Zero-shot Learning; Self-Supervised Learning; Adversarial Robustness; Course Conclusion
- (Optional) Pruning and Model Compression; Neural Architecture Search
Evaluation process
Registering is necessary for students who want to take the examination to obtain the certifications from the IITs. Students must pass the examination with minimum marks to receive the completion certification.
Instructors
IIT Madras (IITM) Frequently Asked Questions (FAQ's)
The candidates must be Senior undergraduate students or post-graduate students who have done their basic course in Machine Learning and have basic knowledge of probability, linear algebra, calculus, and Python.
The certification course will take 12 weeks to complete. The candidates receive all the required training and study materials online and also get the opportunity to access the live sessions.
The candidates are required to pay the examination fee that is Rs 1000/- to appear for the examination and qualify with minimum marks, at least 10 out of 25 percent in assignments and 30 out of 75 percent in the final proctored exam.
This certification course learning applies to all the companies that are using computer vision for their products or services such as Microsoft, Google, Facebook, Apple, TCS, Cognizant, L&T, and others.
Yes, the certification course supports the students with industry expert training and as well as provides them the assignments, transcripts, books, and videos on the subject.