Deep Learning For Visual Computing by NPTEL

Jupyter Notebook Viewer (nbviewer) link to browse the notebooks

Deep learning is a genre of machine learning algorithms that attempt to solve tasks by learning abstraction in data following a stratified description paradigm using non-­linear transformation architectures. When put in simple terms, say you want to make the machine recognize Mr. X standing in front of Mt. E on an image;; this task is a stratified or hierarchical recognition task. At the base of the recognition pyramid would be features which can discriminate flats, lines, curves, sharp angles, color;; higher up will be kernels which use this information to discriminate body parts, trees, natural scenery, clouds, etc.;; higher up it will use this knowledge to recognize humans, animals, mountains, etc.;; and higher up it will learn to recognize Mr. X and Mt. E and finally the apex lexical synthesizer module would say that Mr. X is standing in front of Mt. E. Deep learning is all about how you make machines synthesize this hierarchical logic and also learn these representative features and kernels all by itself. It has been used to solve problems like handwritten character recognition, object and product recognition and localization, image captioning, generating synthetic images to self driving cars. This course would provide you insights to theory and coding practice of deep learning for visual computing through curated exercises with Python and PyTorch on current developments.

INTENDED AUDIENCE: Electrical, Electronics, Computer Sciences

PREREQUISITES: Digital Image Processing, Machine Learning

INDUSTRY SUPPORT: Industry related to Deep Learning and Machine Vision such as

Intel Microsoft Google Nvidia Philips GE Siemens Samsung IBM Apple TCS Infosys Wipro Robert Bosch Baidu Wymo Tesla, etc.

• Week 1: Introduction to Visual Computing and Neural Networks
• Week 2: Multilayer Perceptron to Deep Neural Networks with Autoencoders
• Week 3: Autoencoders for Representation Learning and MLP Initialization
• Week 4: Stacked, Sparse, Denoising Autoencoders and Ladder Training
• Week 5: Cost functions, Learning Rate Dynamics and Optimization
• Week 6: Introduction to Convolutional Neural Networks (CNN) and LeNet
• Week 7: Convolutional Autoencoders and Deep CNN (AlexNet, VGGNet)
• Week 8: Very Deep CNN for Classification (GoogLeNet, ResNet, DenseNet)
• Week 9: Computational Complexity and Transfer Learning of a Network
• Week 10: Object Localization (RCNN) and Semantic Segmentation
• Week 11: Generative Models with Adversarial Learning
• Week 12: Recurrent Neural Networks (RNN) for Video Classification

Elective

Postgraduate

Debdoot Sheeet is an Assistant Professor of Electrical Engineering at the Indian Institute of Technology Kharagpur and founder of SkinCurate Research. He received the MS and PhD degrees in computational medical imaging and machine learning from the Indian Institute of Technology Kharagpur in 2010 and 2014 respectively. He was a DAAD visiting PhD scholar to TU Munich during 2011-­12. His research interests include deep learning and domain adaptation, computational medical imaging, image and multidimensional signal processing, surgical analytics and informatics, visualization and augmented reality technology design. He has widely published in journals including Medical Image Analysis (MedIA), and conferences like the IEEE International Symposium on Biomedical Imaging (ISBI). He is a member of IEEE, SPIE, ACM, IUPRAI and BMESI and serves as an Editor of IEEE Pulse since 2014.

Goodfellow, Y, Bengio, A. Courville, “Deep Learning”, MIT Press, 2016. S. Haykin, “Neural Networks and Learning Machines”,3e,Pearson, 2008.

• The course is free to enroll and learn from. But if you want a certificate, you have to register and write the proctored exam conducted by us in person at any of the designated exam centres.
• The exam is optional for a fee of Rs 1000/- (Rupees one thousand only).
• Date and Time of Exams: 18th October 2020, Morning session 9am to 12 noon; Afternoon Session 2pm to 5pm.
• Registration url: Announcements will be made when the registration form is open for registrations.
• The online registration form has to be filled and the certification exam fee needs to be paid. More details will be made available when the exam registration form is published. If there are any changes, it will be mentioned then.
• Please check the form for more details on the cities where the exams will be held, the conditions you agree to when you fill the form etc.

• Average assignment score = 25% of average of best 8 assignments out of the total 12 assignments given in the course.

• Exam score = 75% of the proctored certification exam score out of 100

• Final score = Average assignment score + Exam score

• YOU WILL BE ELIGIBLE FOR A CERTIFICATE ONLY IF AVERAGE ASSIGNMENT SCORE >=10/25 AND EXAM SCORE >= 30/75.

• If one of the 2 criteria is not met, you will not get the certificate even if the Final score >= 40/100.

• Certificate will have your name, photograph and the score in the final exam with the breakup.It will have the logos of NPTEL and IIT Kharagpur. It will be e-verifiable at nptel.ac.in/noc

• Only the e-certificate will be made available. Hard copies will not be dispatched.