Modules / Lectures


New Assignments
Module NameDownload
W0A1W0A1
W10A1W10A1
W11A1W11A1
W12A1W12A1
W1A1W1A1
W3A1W3A1
W4A1W4A1
W5A1W5A1
W6A1W6A1
W7A1W7A1
W8A1W8A1
W9A1W9A1

Sl.No Chapter Name English
1Lecture 1 : Introduction to Visual ComputingDownload
To be verified
2Lecture 2 : Feature Extraction for Visual ComputingDownload
To be verified
3Lecture 3: Feature Extraction with PythonDownload
To be verified
4Lecture 4: Neural Networks for Visual ComputingDownload
To be verified
5Lecture 5: Classification with Perceptron ModelDownload
To be verified
6Lecture 6 : Introduction to Deep Learning with Neural NetworksDownload
To be verified
7Lecture 7 : Introduction to Deep Learning with Neural NetworksDownload
To be verified
8Lecture 8 : Multilayer Perceptron and Deep Neural NetworksDownload
To be verified
9Lecture 9 : Multilayer Perceptron and Deep Neural NetworksDownload
To be verified
10Lecture 10 : Classification with Multilayer PerceptronDownload
To be verified
11Lecture 11 : Autoencoder for Representation Learning and MLP InitializationDownload
To be verified
12Lecture 12 : MNIST handwritten digits classification using autoencodersDownload
To be verified
13Lecture 13 ; Fashion MNIST classification using autoencodersDownload
To be verified
14Lecture 14 : ALL-IDB Classification using autoencodersDownload
To be verified
15Lecture 15 : Retinal Vessel Detection using autoencodersDownload
To be verified
16Lecture 16 : Stacked AutoencodersDownload
To be verified
17Lecture 17 : MNIST and Fashion MNIST with Stacked AutoencodersDownload
To be verified
18Lecture 18 : Denoising and Sparse AutoencodersDownload
To be verified
19Lecture 19 : Sparse Autoencoders for MNIST classificationDownload
To be verified
20Lecture 20 : Denoising Autoencoders for MNIST classificationDownload
To be verified
21Lecture 21 : Cost FunctionDownload
To be verified
22Lecture 22 : Classification cost functionsDownload
To be verified
23Lecture 23 : Optimization Techniques and Learning RulesDownload
To be verified
24Lecture 24 : Gradient Descent Learning RuleDownload
To be verified
25Lecture 25 : SGD and ADAM Learning RulesDownload
To be verified
26Lecture 26 : Convolutional Neural Network Building BlocksDownload
To be verified
27Lecture 27 : Simple CNN Model: LeNetDownload
To be verified
28Lecture 28 : LeNet DefinitionDownload
To be verified
29Lecture 29 : Training a LeNet for MNIST ClassificationDownload
To be verified
30Lecture 30 : Modifying a LeNet for CIFARDownload
To be verified
31Lecture 31 : Convolutional Autoencoder and Deep CNNDownload
To be verified
32Lecture 32 : Convolutional Autoencoder for Representation LearningDownload
To be verified
33Lecture 33 : AlexNetDownload
To be verified
34Lecture 34 : VGGNetDownload
To be verified
35Lecture 35 : Revisiting AlexNet and VGGNet for Computational ComplexityDownload
To be verified
36Lecture 36: GoogLeNet - Going very deep with convolutionsDownload
To be verified
37Lecture 37 : GoogLeNetDownload
To be verified
38Lecture 38: ResNet - Residual Connections within Very Deep Networks and DenseNet - Densely connected networksDownload
To be verified
39Lecture 39: ResNetDownload
To be verified
40Lecture 40: : DenseNetDownload
To be verified
41Lecture 41 : Space and Computational Complexity in DNNDownload
To be verified
42Lecture 42 : Assessing the space and computational complexity of very deep CNNsDownload
To be verified
43Lecture 43: Domain Adaptation and Transfer Learning in Deep Neural NetworksDownload
To be verified
44Lecture 44 : Transfer Learning a GoogLeNetDownload
To be verified
45Lecture 45 : Transfer Learning a ResNetDownload
To be verified
46Lecture 46 Activation pooling for object localizationDownload
To be verified
47Lecture 47: Region Proposal Networks (rCNN and Faster rCNN)Download
To be verified
48Lecture 48:GAP + rCNNDownload
To be verified
49Lecture 49: Semantic Segmentation with CNNDownload
To be verified
50Lecture 50: UNet and SegNet for Semantic SegmentationDownload
To be verified
51Lecture 51 : Autoencoders and Latent SpacesDownload
To be verified
52Lecture 52 : Principle of Generative ModelingDownload
To be verified
53Lecture 53 : Adversarial AutoencodersDownload
To be verified
54Lecture 54 : Adversarial Autoencoder for Synthetic Sample GenerationDownload
To be verified
55Lecture 55: Adversarial Autoencoder for ClassificationDownload
To be verified
56Lecture 56 : Understanding Video AnalysisDownload
To be verified
57Lecture 57 : Recurrent Neural Networks and Long Short-Term MemoryDownload
To be verified
58Lecture 58 : Spatio-Temporal Deep Learning for Video AnalysisDownload
To be verified
59Lecture 59 : Activity recognition using 3D-CNNDownload
To be verified
60Lecture 60 : Activity recognition using CNN-LSTMDownload
To be verified


Sl.No Language Book link
1EnglishNot Available
2BengaliNot Available
3GujaratiNot Available
4HindiNot Available
5KannadaNot Available
6MalayalamNot Available
7MarathiNot Available
8TamilNot Available
9TeluguNot Available