0

(

ratings

)

2

students

Created by:

Profile Photo

Last updated:

September 25, 2023

Duration:

Unlimited Duration

FREE

This course includes:

Unlimited Duration

Badge on Completion

Certificate of completion

Unlimited Duration

Description

Deep Learning for Visual Computing. Instructor: Prof. Debdoot Sheet, Department of Electrical Engineering, IIT Kharagpur.

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 nonlinear 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. (from nptel.ac.in)

Course Curriculum

  • Lecture 01 – Introduction to Visual Computing Unlimited
  • Lecture 02 – Feature Extraction for Visual Computing Unlimited
  • Lecture 03 – Feature Extraction with Python Unlimited
  • Lecture 04 – Neural Networks for Visual Computing Unlimited
  • Lecture 05 – Classification with Perceptron Model Unlimited
  • Lecture 06 – Introduction to Deep Learning with Neural Networks Unlimited
  • Lecture 07 – Introduction to Deep Learning with Neural Networks (cont.) Unlimited
  • Lecture 08 – Multilayer Perceptron and Deep Neural Networks Unlimited
  • Lecture 09 – Multilayer Perceptron and Deep Neural Networks (cont.) Unlimited
  • Lecture 10 – Classification with Multilayer Perceptron Unlimited
  • Lecture 11 – Autoencoder for Representation Learning and MLP Initialization Unlimited
  • Lecture 12 – MNIST Handwritten Digits Classification using Autoencoders Unlimited
  • Lecture 13 – Fashion MNIST Classification using Autoencoders Unlimited
  • Lecture 14 – ALL-IDB Classification using Autoencoders Unlimited
  • Lecture 15 – Retinal Vessel Detection using Autoencoders Unlimited
  • Lecture 16 – Stacked Autoencoders Unlimited
  • Lecture 17 – MNIST and Fashion MNIST with Stacked Autoencoders Unlimited
  • Lecture 18 – Sparse and Denoising Autoencoder Unlimited
  • Lecture 19 – Sparse Autoencoders for MNIST Classification Unlimited
  • Lecture 20 – Denoising Autoencoders for MNIST Classification Unlimited
  • Lecture 21 – Cost Functions Unlimited
  • Lecture 22 – Classification Cost Functions Unlimited
  • Lecture 23 – Optimization Techniques and Learning Rules Unlimited
  • Lecture 24 – Gradient Descent Learning Rule Unlimited
  • Lecture 25 – SGD and ADAM Learning Rules Unlimited
  • Lecture 26 – Convolutional Neural Network Building Blocks Unlimited
  • Lecture 27 – Simple CNN Model: LeNet Unlimited
  • Lecture 28 – LeNet Definition Unlimited
  • Lecture 29 – Training a LeNet for MNIST Classification Unlimited
  • Lecture 30 – Modifying a LeNet for CIFAR Unlimited
  • Lecture 31 – Convolutional Autoencoder and Deep CNN Unlimited
  • Lecture 32 – Convolutional Autoencoder for Representation Learning Unlimited
  • Lecture 33 – AlexNet Unlimited
  • Lecture 34 – VGGNet Unlimited
  • Lecture 35 – Revisiting AlexNet and VGGNet for Computational Complexity Unlimited
  • Lecture 36 – GoogLeNet – Going Very Deep with Convolutions Unlimited
  • Lecture 37 – GoogLeNet Unlimited
  • Lecture 38 – ResNet – Residual Connections within Very Deep Networks and DenseNet … Unlimited
  • Lecture 39 – ResNet Unlimited
  • Lecture 40 – DenseNet Unlimited
  • Lecture 41 – Space and Computational Complexity in DNN Unlimited
  • Lecture 42 – Assessing the Space and Computational Complexity of Very Deep CNNs Unlimited
  • Lecture 43 – Domain Adaptation and Transfer Learning in Deep Neural Networks Unlimited
  • Lecture 44 – Transfer Learning a GoogLeNet Unlimited
  • Lecture 45 – Transfer Learning a ResNet Unlimited
  • Lecture 46 – Activation Pooling for Object Localization Unlimited
  • Lecture 47 – Regional Proposal Networks (rCNN and Faster rCNN) Unlimited
  • Lecture 48 – GAP + rCNN Unlimited
  • Lecture 49 – Semantic Segmentation with CNN Unlimited
  • Lecture 50 – UNet and SegNet for Semantic Segmentation Unlimited
  • Lecture 51 – Autoencoders and Latent Spaces Unlimited
  • Lecture 52 – Principle of Generative Modeling Unlimited
  • Lecture 53 – Adversarial Autoencoders Unlimited
  • Lecture 54 – Adversarial Autoencoder for Synthetic Sample Generation Unlimited
  • Lecture 55 – Adversarial Autoencoder for Classification Unlimited
  • Lecture 56 – Understanding Video Analysis Unlimited
  • Lecture 57 – Recurrent Neural Networks and Long Short – Term Memory Unlimited
  • Lecture 58 – Spatio-Temporal Deep Learning for Video Analysis Unlimited
  • Lecture 59 – Activity Recognition using 3D-CNN Unlimited
  • Lecture 60 – Activity Recognition using CNN-LSTM Unlimited

About the instructor

5 5

Instructor Rating

6

Reviews

4637

Courses

24151

Students

Profile Photo
OpenCoursa
We are an educational and skills marketplace to accommodate the needs of skills enhancement and free equal education across the globe to the millions. We are bringing courses and trainings every single day for our users. We welcome everyone woth all ages, all background to learn. There is so much available to learn and deliver to the people.