NPTEL : NOC:Deep Learning (Prof. P.K. Biswas) (Computer Science and Engineering)

Co-ordinators : Prof. P.K. Biswas


Lecture 1 - Introduction

Lecture 2 - Feature Descriptor - I

Lecture 3 - Feature Descriptor - II

Lecture 4 - Bayesian Learning - I

Lecture 5 - Bayesian Learning - II

Lecture 6 - Discriminant Function - I

Lecture 7 - Discriminant Function - II

Lecture 8 - Discriminant Function - III

Lecture 9 - Linear Classifier - I

Lecture 10 - Linear Classifier - II

Lecture 11 - Support Vector Machine - I

Lecture 12 - Support Vector Machine - II

Lecture 13 - Linear Machine

Lecture 14 - Multiclass Support Vector Machine - I

Lecture 15 - Multiclass Support Vector Machine - II

Lecture 16 - Optimization

Lecture 17 - Optimization Techniques in Machine Learning

Lecture 18 - Nonlinear Functions

Lecture 19 - Introduction to Neural Network

Lecture 20 - Neural Network - II

Lecture 21 - Multilayer Perceptron - I

Lecture 22 - Multilayer Perceptron - II

Lecture 23 - Backpropagation Learning

Lecture 24 - Loss Function

Lecture 25 - Backpropagation Learning- Example - I

Lecture 26 - Backpropagation Learning- Example - II

Lecture 27 - Backpropagation Learning- Example - III

Lecture 28 - Autoencoder

Lecture 29 - Autoencoder Vs PCA - I

Lecture 30 - Autoencoder Vs PCA - II

Lecture 31 - Autoencoder Training

Lecture 32 - Autoencoder Variants - I

Lecture 33 - Autoencoder Variants - II

Lecture 34 - Convolution

Lecture 35 - Cross Correlation

Lecture 36 - CNN Architecture

Lecture 37 - MLP versus CNN, Popular CNN Architecture: LeNet

Lecture 38 - Popular CNN Architecture: AlexNet

Lecture 39 - Popular CNN Architecture: VGG16, Transfer Learning

Lecture 40 - Vanishing and Exploding Gradient

Lecture 41 - GoogleNet

Lecture 42 - ResNet, Optimisers: Momentum Optimiser

Lecture 43 - Optimisers: Momentum and Nesterov Accelerated Gradient (NAG) Optimiser

Lecture 44 - Optimisers: Adagrad Optimiser

Lecture 45 - Optimisers: RMSProp, AdaDelta and Adam Optimiser

Lecture 46 - Normalization

Lecture 47 - Batch Normalization - I

Lecture 48 - Batch Normalization - II

Lecture 49 - Layer, Instance, Group Normalization

Lecture 50 - Training Trick, Regularization,Early Stopping

Lecture 51 - Face Recognition

Lecture 52 - Deconvolution Layer

Lecture 53 - Semantic Segmentation - I

Lecture 54 - Semantic Segmentation - II

Lecture 55 - Semantic Segmentation - III

Lecture 56 - Image Denoising

Lecture 57 - Variational Autoencoder - I

Lecture 58 - Variational Autoencoder - II

Lecture 59 - Variational Autoencoder - III

Lecture 60 - Generative Adversarial Network