DeepLearning - Mitesh Khapra, SKS Iyengar || IIT Ropar and Madras - NPTEL
4.0
(4)
28 learners
What you'll learn
This course includes
- 37.3 hours of video
- Certificate of completion
- Access on mobile and TV
Course content
1 modules • 156 lessons • 37.3 hours of video
DeepLearning - Mitesh Khapra, SKS Iyengar || IIT Ropar and Madras - NPTEL
156 lessons
• 37.3 hours
DeepLearning - Mitesh Khapra, SKS Iyengar || IIT Ropar and Madras - NPTEL
156 lessons
• 37.3 hours
- Deep Learning - Course Introduction 06:59
- Deep Learning(CS7015): Lec 1.1 Biological Neuron 06:58
- Deep Learning(CS7015): Lec 1.2 From Spring to Winter of AI 13:44
- Deep Learning(CS7015): Lec 1.3 The Deep Revival 07:57
- Deep Learning(CS7015): Lec 1.4 From Cats to Convolutional Neural Networks 03:32
- Deep Learning(CS7015): Lec 1.5 Faster, higher, stronger 02:48
- Deep Learning(CS7015): Lec 1.6 The Curious Case of Sequences 06:36
- Deep Learning(CS7015): Lec 1.7 Beating humans at their own games (literally) 02:03
- Deep Learning(CS7015): Lec 1.8 The Madness (2013-) 04:55
- Deep Learning(CS7015): Lec 1.9 (Need for) Sanity 04:46
- Deep Learning(CS7015): Lec 2.1 Motivation from Biological Neurons 07:32
- Deep Learning(CS7015): Lec 2.2 McCulloch Pitts Neuron, Thresholding Logic 13:39
- Deep Learning(CS7015): Lec 2.3 Perceptrons 11:00
- Deep Learning(CS7015): Lec 2.4 Error and Error Surfaces 04:21
- Deep Learning(CS7015): Lec 2.5 Perceptron Learning Algorithm 13:35
- Deep Learning(CS7015): Lec 2.6 Proof of Convergence of Perceptron Learning Algorithm 15:38
- Deep Learning(CS7015): Lec 2.7 Linearly Separable Boolean Functions 06:18
- Deep Learning(CS7015): Lec 2.8 Representation Power of a Network of Perceptrons 13:30
- Deep Learning(CS7015): Lec 3.1 Sigmoid Neuron 12:30
- Deep Learning(CS7015): Lec 3.2 A typical Supervised Machine Learning Setup 16:02
- Deep Learning(CS7015): Lec 3.3 Learning Parameters: (Infeasible) guess work 11:53
- Deep Learning(CS7015): Lec 3.4 Learning Parameters: Gradient Descent 31:21
- Deep Learning(CS7015): Lec 3.5 Representation Power of Multilayer Network of Sigmoid Neurons 35:35
- Deep Learning(CS7015): Lec 4.1 Feedforward Neural Networks (a.k.a multilayered network of neurons) 18:46
- Deep Learning(CS7015): Lec 4.2 Learning Paramters of Feedforward Neural Networks (Intuition) 06:57
- Deep Learning(CS7015): Lec 4.3 Output functions and Loss functions 26:50
- Deep Learning(CS7015): Lec 4.4 Backpropagation (Intuition) 13:52
- Deep Learning(CS7015): Lec 4.5 Backpropagation: Computing Gradients w.r.t. the Output Units 17:08
- Deep Learning(CS7015): Lec 4.6 Backpropagation: Computing Gradients w.r.t. Hidden Units 21:02
- Deep Learning(CS7015): Lec 4.7 Backpropagation: Computing Gradients w.r.t. Parameters 12:45
- Deep Learning(CS7015): Lec 4.8 Backpropagation: Pseudo code 05:59
- Deep Learning(CS7015): Lec 4.9 Derivative of the activation function 01:53
- Deep Learning(CS7015): Lec 6.6 PCA : Interpretation 3 04:02
- Deep Learning(CS7015): Lec 4.10 Information content, Entropy & cross entropy 44:28
- Deep Learning(CS7015): Lec 5.1 & Lec 5.2 Recap: Learning Parameters: Guess Work, Gradient Descent 09:11
- Deep Learning(CS7015): Lec 5.3 Contours Maps 11:10
- Deep Learning(CS7015): Lec 5.4 Momentum based Gradient Descent 18:45
- Deep Learning(CS7015): Lec 5.5 Nesterov Accelerated Gradient Descent 11:59
- Deep Learning(CS7015): Lec 5.6 Stochastic And Mini-Batch Gradient Descent 14:12
- Deep Learning(CS7015): Lec 5.7 Tips for Adjusting Learning Rate and Momentum 13:21
- Deep Learning(CS7015): Lec 5.8 Line Search 09:21
- Deep Learning(CS7015): Lec 5.9 Gradient Descent with Adaptive Learning Rate 40:48
- Deep Learning(CS7015): Lec 5.9 (Part-2) Bias Correction in Adam 10:12
- Deep Learning(CS7015): Lec 6.1 Eigenvalues and Eigenvectors 17:49
- Deep Learning(CS7015): Lec 6.2 Linear Algebra : Basic Definitions 11:18
- Deep Learning(CS7015): Lec 6.3 Eigenvalue Decompositon 09:45
- Deep Learning(CS7015): Lec 6.4 Principal Component Analysis and its Interpretations 25:42
- Deep Learning(CS7015): Lec 6.5 PCA : Interpretation 2 17:08
- Deep Learning(CS7015): Lec 6.6 (Part-2) PCA : Interpretation 3 (Contd.) 02:11
- Deep Learning(CS7015): Lec 6.7 PCA : Practical Example 12:12
- Deep Learning(CS7015): Lec 6.8 Singular Value Decomposition 26:00
- Deep Learning(CS7015): Lec 7.1 Introduction to Autoncoders 52:33
- Deep Learning(CS7015): Lec 7.2 Link between PCA and Autoencoders 17:39
- Deep Learning(CS7015): Lec 7.3 Regularization in autoencoders (Motivation) 12:27
- Deep Learning(CS7015): Lec 7.4 Denoising Autoencoders 26:18
- Deep Learning(CS7015): Lec 7.5 Sparse Autoencoders 09:12
- Deep Learning(CS7015): Lec 7.6 Contractive Autoencoders 08:39
- Deep Learning(CS7015): Lec 8.1 Bias and Variance 10:53
- Deep Learning(CS7015): Lec 8.2 Train error vs Test error 11:24
- Deep Learning(CS7015): Lec 8.2 (Part-2) Train error vs Test error (Recap) 18:01
- Deep Learning(CS7015): Lec 8.3 True error and Model complexity 08:48
- Deep Learning(CS7015): Lec 8.4 L2 regularization 24:13
- Deep Learning(CS7015): Lec 8.5 Dataset augmentation 06:23
- Deep Learning(CS7015): Lec 8.6 Parameter sharing and tying 01:31
- Deep Learning(CS7015): Lec 8.7 Adding Noise to the inputs 08:03
- Deep Learning(CS7015): Lec 8.8 Adding Noise to the outputs 04:51
- Deep Learning(CS7015): Lec 8.9 Early stopping 11:58
- Deep Learning(CS7015): Lec 8.10 Ensemble Methods 07:54
- Deep Learning(CS7015): Lec 8.11 Dropout 16:37
- Deep Learning(CS7015): Lec 9.1 A quick recap of training deep neural networks 06:21
- Deep Learning(CS7015): Lec 9.2 Unsupervised pre-training 24:57
- Deep Learning(CS7015): Lec 9.3 Better activation functions 28:09
- Deep Learning(CS7015): Lec 9.4 Better initialization strategies 26:31
- Deep Learning(CS7015): Lec 9.5 Batch Normalization 15:44
- Deep Learning(CS7015): Lec 10.1 One-hot representations of words 09:26
- Deep Learning(CS7015): Lec 10.2 Distributed Representations of words 12:06
- Deep Learning(CS7015): Lec 10.3 SVD for learning word representations 14:41
- Deep Learning(CS7015): Lec 10.3 (Part-2) SVD for learning word representations (Contd.) 01:41
- Deep Learning(CS7015): Lec 10.4 Continuous bag of words model 36:36
- Deep Learning(CS7015): Lec 10.5 Skip-gram model 10:59
- Deep Learning(CS7015): Lec 10.5 (Part-2) Skip-gram model (Contd.) 08:35
- Deep Learning(CS7015): Lec 10.6 Contrastive estimation 07:05
- Deep Learning(CS7015): Lec 10.7 Hierarchical softmax 13:30
- Deep Learning(CS7015): Lec 10.8 GloVe representations 07:59
- Deep Learning(CS7015): Lec 10.9 Evaluating word representations 08:51
- Deep Learning(CS7015): Lec 10.10 Relation between SVD and Word2Vec 04:16
- Deep Learning(CS7015): Lec 11.1 The convolution operation 18:29
- Deep Learning(CS7015): Lec 11.2 Relation between input size, output size and filter size 12:27
- Deep Learning(CS7015): Lec 11.3 Convolutional Neural Networks 16:58
- Deep Learning(CS7015): Lec 11.3 (Part-2) Convolutional Neural Networks (Contd.) 17:39
- Deep Learning(CS7015): Lec 11.4 CNNs (success stories on ImageNet) 20:49
- Deep Learning(CS7015): Lec 11.4 (Par-2) CNNs (success stories on ImageNet) (Contd.) 02:57
- Deep Learning(CS7015): Lec 11.5 Image Classification continued (GoogLeNet and ResNet) 22:50
- Deep Learning(CS7015): Lec 12.1 Visualizing patches which maximally activate a neuron 06:36
- Deep Learning(CS7015): Lec 12.2 Visualizing filters of a CNN 06:31
- Deep Learning(CS7015): Lec 12.3 Occlusion experiments 06:21
- Deep Learning(CS7015): Lec 12.4 Finding influence of input pixels using backpropagation 06:12
- Deep Learning(CS7015): Lec 12.5 Guided Backpropagation 04:52
- Deep Learning(CS7015): Lec 12.6 Optimization over images 10:28
- Deep Learning(CS7015): Lec 12.7 Create images from embeddings 06:20
- Deep Learning(CS7015): Lec 12.8 Deep Dream 11:19
- Deep Learning(CS7015): Lec 12.9 Deep Art 05:49
- Deep Learning(CS7015): Lec 12.10 Fooling Deep Convolutional Neural Networks 06:43
- Deep Learning(CS7015): Lec 13.1 Sequence Learning Problems 08:44
- Deep Learning(CS7015): Lec 13.2 Recurrent Neural Networks 09:48
- Deep Learning(CS7015): Lec 13.3 Backpropagation through time 14:24
- Deep Learning(CS7015): Lec 13.4 The problem of Exploding and Vanishing Gradients 11:04
- Deep Learning(CS7015): Lec 13.5 Some Gory Details 06:58
- Deep Learning(CS7015): Lec 14.1 Selective Read, Selective Write, Selective Forget 09:18
- Deep Learning(CS7015): Lec 14.2 Long Short Term Memory(LSTM) and Gated Recurrent Units(GRUs) 31:20
- Deep Learning(CS7015): Lec 14.3 How LSTMs avoid the problem of vanishing gradients 08:11
- Deep Learning(CS7015): Lec 14.3 (Part-2) How LSTMs avoid the problem of vanishing gradients (Contd.) 23:53
- Deep Learning(CS7015): Lec 15.1 Introduction to Encoder Decoder Models 21:55
- Deep Learning(CS7015): Lec 15.2 Applications of Encoder Decoder models 17:34
- Deep Learning(CS7015): Lec 15.3 Attention Mechanism 27:38
- Deep Learning(CS7015): Lec 15.3 (Part-2) Attention Mechanism (Contd.) 02:38
- Deep Learning(CS7015): Lec 15.4 Attention over images 11:31
- Deep Learning(CS7015): Lec 15.5 Hierarchical Attention 20:32
- Deep Learning Part - II Introduction 04:02
- Deep Learning Part - II (CS7015): Lec 17.1 Markov Networks: Motivation 16:16
- Deep Learning Part - II (CS7015): Lec 17.2 Factors in Markov Network 21:56
- Deep Learning Part - II (CS7015): Lec 17.3 Local Independencies in a Markov Network 15:24
- Deep Learning Part - II (CS7015): Lec 16.0 Recap of Probability Theory 15:08
- Deep Learning Part - II (CS7015): Lec 16.1 Why are we interested in Joint Distributions 06:23
- Deep Learning Part - II (CS7015): Lec 16.2 How do we represent a joint distribution 04:26
- Deep Learning Part - II (CS7015): Lec 16.3 Can we represent the joint distribution more compactly 15:40
- Deep Learning Part - II (CS7015): Lec 16.4 Can we use a graph to represent a joint distribution 17:07
- Deep Learning Part - II : Lec 16.5 Different types of reasoning encoded in a Bayesian Network 16:18
- Deep Learning Part - II (CS7015): Lec 16.6 Independencies encoded by a Bayesian Network(Case 1) 06:12
- Deep Learning Part - II (CS7015): Lec 16.7 Independencies encoded by a Bayesian Network(Case 2) 05:04
- Deep Learning Part - II (CS7015): Lec 16.8 Independencies encoded by a Bayesian Network(Case 3) 03:39
- Deep Learning Part - II (CS7015): Lec 16.9 Bayesian Networks : Formal Semantics 02:55
- Deep Learning Part - II (CS7015): Lec 16.10 I-Maps 12:54
- Deep Learning Part - II (CS7015): Lec 18.1 Joint Distributions 27:59
- Deep Learning Part - II (CS7015): Lec 18.2 The concept of a latent variable 30:03
- Deep Learning Part - II (CS7015): Lec 18.3 Restricted Boltzmann Machines 16:10
- Deep Learning Part - II (CS7015): Lec 18.4 RBMs as Stochastic Neural Networks 14:34
- Deep Learning Part - II (CS7015): Lec 18.5 Unsupervised Learning with RBMs 05:41
- Deep Learning Part - II (CS7015): Lec 18.6 Computing the gradient of the log likelihood 11:58
- Deep Learning Part - II (CS7015): Lec 18.7 Motivation for Sampling 14:01
- Deep Learning Part - II (CS7015): Lec 18.8 Motivation for Sampling - Part - 02 02:45
- Deep Learning Part - II (CS7015): Lec 19.1 Markov Chains 34:40
- Deep Learning Part - II (CS7015): Lec 19.2 Why de we care about Markov Chains ? 10:46
- Deep Learning Part - II (CS7015): Lec 19.3 Setting up a Markov Chain for RBMs 47:55
- Deep Learning Part - II (CS7015): Lec 19.4Training RBMs Using Gibbs Sampling 21:07
- Deep Learning Part - II (CS7015): Lec 19.5 Training RBMS Using Contrastive Divergence 11:10
- Deep Learning Part - II (CS7015): Lec 20.1 Revisiting Autoencoders 20:11
- Deep Learning Part - II (CS7015): Lec 20.2 Variational Autoencoders: The Neural Network Perspective 34:32
- Deep Learning Part - II (CS7015): Lec 20.3 Variational Autoencoders: The Graphical model perspective 46:02
- Deep Learning Part - II (CS7015): Lec 21.1 Neural Autoregressive Density Estimator (NADE) 36:20
- Deep Learning Part - II (CS7015): Lec 21.2 Masked Autoencoder Density Estimator (MADE) 35:21
- Deep Learning Part - II (CS7015): Lec 22.1 Generative Adversarial Networks - The Intuition 25:00
- Deep Learning Part - II (CS7015): Lec 22.2 Generative Adversarial Networks - Architecture 09:21
- Deep Learning Part - II (CS7015): Lec 22.3 Generative Adversarial Networks - The Math Behind it 22:30
- Lec 22.4 Generative Adversarial Networks - Some Cool Stuff and Applications 07:32
- Deep Learning Part - II (CS7015): Lec 22.5 Bringing it all together (the deep generative summary) 08:23
Take this course with you
Download the app to continue lessons from your phone anytime.
