| Sl.No | Chapter Name | MP4 Download |
|---|---|---|
| 1 | Lecture 1 : Introduction to Visual Computing | Download |
| 2 | Lecture 2 : Feature Extraction for Visual Computing | Download |
| 3 | Lecture 3: Feature Extraction with Python | Download |
| 4 | Lecture 4: Neural Networks for Visual Computing | Download |
| 5 | Lecture 5: Classification with Perceptron Model | Download |
| 6 | Lecture 6 : Introduction to Deep Learning with Neural Networks | Download |
| 7 | Lecture 7 : Introduction to Deep Learning with Neural Networks | Download |
| 8 | Lecture 8 : Multilayer Perceptron and Deep Neural Networks | Download |
| 9 | Lecture 9 : Multilayer Perceptron and Deep Neural Networks | Download |
| 10 | Lecture 10 : Classification with Multilayer Perceptron | Download |
| 11 | Lecture 11 : Autoencoder for Representation Learning and MLP Initialization | Download |
| 12 | Lecture 12 : MNIST handwritten digits classification using autoencoders | Download |
| 13 | Lecture 13 ; Fashion MNIST classification using autoencoders | Download |
| 14 | Lecture 14 : ALL-IDB Classification using autoencoders | Download |
| 15 | Lecture 15 : Retinal Vessel Detection using autoencoders | Download |
| 16 | Lecture 16 : Stacked Autoencoders | Download |
| 17 | Lecture 17 : MNIST and Fashion MNIST with Stacked Autoencoders | Download |
| 18 | Lecture 18 : Denoising and Sparse Autoencoders | Download |
| 19 | Lecture 19 : Sparse Autoencoders for MNIST classification | Download |
| 20 | Lecture 20 : Denoising Autoencoders for MNIST classification | Download |
| 21 | Lecture 21 : Cost Function | Download |
| 22 | Lecture 22 : Classification cost functions | Download |
| 23 | Lecture 23 : Optimization Techniques and Learning Rules | Download |
| 24 | Lecture 24 : Gradient Descent Learning Rule | Download |
| 25 | Lecture 25 : SGD and ADAM Learning Rules | Download |
| 26 | Lecture 26 : Convolutional Neural Network Building Blocks | Download |
| 27 | Lecture 27 : Simple CNN Model: LeNet | Download |
| 28 | Lecture 28 : LeNet Definition | Download |
| 29 | Lecture 29 : Training a LeNet for MNIST Classification | Download |
| 30 | Lecture 30 : Modifying a LeNet for CIFAR | Download |
| 31 | Lecture 31 : Convolutional Autoencoder and Deep CNN | Download |
| 32 | Lecture 32 : Convolutional Autoencoder for Representation Learning | Download |
| 33 | Lecture 33 : AlexNet | Download |
| 34 | Lecture 34 : VGGNet | Download |
| 35 | Lecture 35 : Revisiting AlexNet and VGGNet for Computational Complexity | Download |
| 36 | Lecture 36: GoogLeNet - Going very deep with convolutions | Download |
| 37 | Lecture 37 : GoogLeNet | Download |
| 38 | Lecture 38: ResNet - Residual Connections within Very Deep Networks and DenseNet - Densely connected networks | Download |
| 39 | Lecture 39: ResNet | Download |
| 40 | Lecture 40: : DenseNet | Download |
| 41 | Lecture 41 : Space and Computational Complexity in DNN | Download |
| 42 | Lecture 42 : Assessing the space and computational complexity of very deep CNNs | Download |
| 43 | Lecture 43: Domain Adaptation and Transfer Learning in Deep Neural Networks | Download |
| 44 | Lecture 44 : Transfer Learning a GoogLeNet | Download |
| 45 | Lecture 45 : Transfer Learning a ResNet | Download |
| 46 | Lecture 46 Activation pooling for object localization | Download |
| 47 | Lecture 47: Region Proposal Networks (rCNN and Faster rCNN) | Download |
| 48 | Lecture 48:GAP + rCNN | Download |
| 49 | Lecture 49: Semantic Segmentation with CNN | Download |
| 50 | Lecture 50: UNet and SegNet for Semantic Segmentation | Download |
| 51 | Lecture 51 : Autoencoders and Latent Spaces | Download |
| 52 | Lecture 52 : Principle of Generative Modeling | Download |
| 53 | Lecture 53 : Adversarial Autoencoders | Download |
| 54 | Lecture 54 : Adversarial Autoencoder for Synthetic Sample Generation | Download |
| 55 | Lecture 55: Adversarial Autoencoder for Classification | Download |
| 56 | Lecture 56 : Understanding Video Analysis | Download |
| 57 | Lecture 57 : Recurrent Neural Networks and Long Short-Term Memory | Download |
| 58 | Lecture 58 : Spatio-Temporal Deep Learning for Video Analysis | Download |
| 59 | Lecture 59 : Activity recognition using 3D-CNN | Download |
| 60 | Lecture 60 : Activity recognition using CNN-LSTM | Download |
| Sl.No | Chapter Name | English |
|---|---|---|
| 1 | Lecture 1 : Introduction to Visual Computing | Download To be verified |
| 2 | Lecture 2 : Feature Extraction for Visual Computing | Download To be verified |
| 3 | Lecture 3: Feature Extraction with Python | Download To be verified |
| 4 | Lecture 4: Neural Networks for Visual Computing | Download To be verified |
| 5 | Lecture 5: Classification with Perceptron Model | Download To be verified |
| 6 | Lecture 6 : Introduction to Deep Learning with Neural Networks | Download To be verified |
| 7 | Lecture 7 : Introduction to Deep Learning with Neural Networks | Download To be verified |
| 8 | Lecture 8 : Multilayer Perceptron and Deep Neural Networks | Download To be verified |
| 9 | Lecture 9 : Multilayer Perceptron and Deep Neural Networks | Download To be verified |
| 10 | Lecture 10 : Classification with Multilayer Perceptron | Download To be verified |
| 11 | Lecture 11 : Autoencoder for Representation Learning and MLP Initialization | Download To be verified |
| 12 | Lecture 12 : MNIST handwritten digits classification using autoencoders | Download To be verified |
| 13 | Lecture 13 ; Fashion MNIST classification using autoencoders | Download To be verified |
| 14 | Lecture 14 : ALL-IDB Classification using autoencoders | Download To be verified |
| 15 | Lecture 15 : Retinal Vessel Detection using autoencoders | Download To be verified |
| 16 | Lecture 16 : Stacked Autoencoders | Download To be verified |
| 17 | Lecture 17 : MNIST and Fashion MNIST with Stacked Autoencoders | Download To be verified |
| 18 | Lecture 18 : Denoising and Sparse Autoencoders | Download To be verified |
| 19 | Lecture 19 : Sparse Autoencoders for MNIST classification | Download To be verified |
| 20 | Lecture 20 : Denoising Autoencoders for MNIST classification | Download To be verified |
| 21 | Lecture 21 : Cost Function | Download To be verified |
| 22 | Lecture 22 : Classification cost functions | Download To be verified |
| 23 | Lecture 23 : Optimization Techniques and Learning Rules | Download To be verified |
| 24 | Lecture 24 : Gradient Descent Learning Rule | Download To be verified |
| 25 | Lecture 25 : SGD and ADAM Learning Rules | Download To be verified |
| 26 | Lecture 26 : Convolutional Neural Network Building Blocks | Download To be verified |
| 27 | Lecture 27 : Simple CNN Model: LeNet | Download To be verified |
| 28 | Lecture 28 : LeNet Definition | Download To be verified |
| 29 | Lecture 29 : Training a LeNet for MNIST Classification | Download To be verified |
| 30 | Lecture 30 : Modifying a LeNet for CIFAR | Download To be verified |
| 31 | Lecture 31 : Convolutional Autoencoder and Deep CNN | Download To be verified |
| 32 | Lecture 32 : Convolutional Autoencoder for Representation Learning | Download To be verified |
| 33 | Lecture 33 : AlexNet | Download To be verified |
| 34 | Lecture 34 : VGGNet | Download To be verified |
| 35 | Lecture 35 : Revisiting AlexNet and VGGNet for Computational Complexity | Download To be verified |
| 36 | Lecture 36: GoogLeNet - Going very deep with convolutions | Download To be verified |
| 37 | Lecture 37 : GoogLeNet | Download To be verified |
| 38 | Lecture 38: ResNet - Residual Connections within Very Deep Networks and DenseNet - Densely connected networks | Download To be verified |
| 39 | Lecture 39: ResNet | Download To be verified |
| 40 | Lecture 40: : DenseNet | Download To be verified |
| 41 | Lecture 41 : Space and Computational Complexity in DNN | Download To be verified |
| 42 | Lecture 42 : Assessing the space and computational complexity of very deep CNNs | Download To be verified |
| 43 | Lecture 43: Domain Adaptation and Transfer Learning in Deep Neural Networks | Download To be verified |
| 44 | Lecture 44 : Transfer Learning a GoogLeNet | Download To be verified |
| 45 | Lecture 45 : Transfer Learning a ResNet | Download To be verified |
| 46 | Lecture 46 Activation pooling for object localization | Download To be verified |
| 47 | Lecture 47: Region Proposal Networks (rCNN and Faster rCNN) | Download To be verified |
| 48 | Lecture 48:GAP + rCNN | Download To be verified |
| 49 | Lecture 49: Semantic Segmentation with CNN | Download To be verified |
| 50 | Lecture 50: UNet and SegNet for Semantic Segmentation | Download To be verified |
| 51 | Lecture 51 : Autoencoders and Latent Spaces | Download To be verified |
| 52 | Lecture 52 : Principle of Generative Modeling | Download To be verified |
| 53 | Lecture 53 : Adversarial Autoencoders | Download To be verified |
| 54 | Lecture 54 : Adversarial Autoencoder for Synthetic Sample Generation | Download To be verified |
| 55 | Lecture 55: Adversarial Autoencoder for Classification | Download To be verified |
| 56 | Lecture 56 : Understanding Video Analysis | Download To be verified |
| 57 | Lecture 57 : Recurrent Neural Networks and Long Short-Term Memory | Download To be verified |
| 58 | Lecture 58 : Spatio-Temporal Deep Learning for Video Analysis | Download To be verified |
| 59 | Lecture 59 : Activity recognition using 3D-CNN | Download To be verified |
| 60 | Lecture 60 : Activity recognition using CNN-LSTM | Download To be verified |
| Sl.No | Language | Book link |
|---|---|---|
| 1 | English | Not Available |
| 2 | Bengali | Not Available |
| 3 | Gujarati | Not Available |
| 4 | Hindi | Not Available |
| 5 | Kannada | Not Available |
| 6 | Malayalam | Not Available |
| 7 | Marathi | Not Available |
| 8 | Tamil | Not Available |
| 9 | Telugu | Not Available |