Modules / Lectures
Module NameDownload
Week_01_Assignment_01Week_01_Assignment_01
Week_02_Assignment_02Week_02_Assignment_02
Week_03_Assignment_03Week_03_Assignment_03
Week_04_Assignment_04Week_04_Assignment_04
Week_05_Assignment_05Week_05_Assignment_05
Week_06_Assignment_06Week_06_Assignment_06
Week_07_Assignment_07Week_07_Assignment_07
Week_08_Assignment_08Week_08_Assignment_08
Week_09_Assignment_09Week_09_Assignment_09
Week_10_Assignment_10Week_10_Assignment_10
Week_11_Assignment_11Week_11_Assignment_11
Week_12_Assignment_12Week_12_Assignment_12
noc18_cs41_Assignment1noc18_cs41_Assignment1
noc18_cs41_Assignment10noc18_cs41_Assignment10
noc18_cs41_Assignment11noc18_cs41_Assignment11
noc18_cs41_Assignment12noc18_cs41_Assignment12
noc18_cs41_Assignment2noc18_cs41_Assignment2
noc18_cs41_Assignment3noc18_cs41_Assignment3
noc18_cs41_Assignment4noc18_cs41_Assignment4
noc18_cs41_Assignment5noc18_cs41_Assignment5
noc18_cs41_Assignment6noc18_cs41_Assignment6
noc18_cs41_Assignment7noc18_cs41_Assignment7
noc18_cs41_Assignment8noc18_cs41_Assignment8
noc18_cs41_Assignment9noc18_cs41_Assignment9


Sl.No Chapter Name MP4 Download
1Biological NeuronDownload
2 From Spring to Winter of AIDownload
3The Deep RevivalDownload
4From Cats to Convolutional Neural NetworksDownload
5Faster, higher, strongerDownload
6The Curious Case of SequencesDownload
7Beating humans at their own games (literally)Download
8 The Madness (2013-)Download
9(Need for) SanityDownload
10Motivation from Biological NeuronsDownload
11McCulloch Pitts Neuron, Thresholding LogicDownload
12PerceptronsDownload
13Error and Error SurfacesDownload
14Perceptron Learning AlgorithmDownload
15Proof of Convergence of Perceptron Learning AlgorithmDownload
16Deep Learning(CS7015): Linearly Separable Boolean FunctionsDownload
17Deep Learning(CS7015): Representation Power of a Network of PerceptronsDownload
18Deep Learning(CS7015): Sigmoid NeuronDownload
19Deep Learning(CS7015): A typical Supervised Machine Learning SetupDownload
20Deep Learning(CS7015): Learning Parameters: (Infeasible) guess workDownload
21Deep Learning(CS7015): Learning Parameters: Gradient DescentDownload
22Deep Learning(CS7015): Representation Power of Multilayer Network of Sigmoid NeuronsDownload
23Feedforward Neural Networks (a.k.a multilayered network of neurons)Download
24Learning Paramters of Feedforward Neural Networks (Intuition)Download
25Output functions and Loss functionsDownload
26Backpropagation (Intuition)Download
27Backpropagation: Computing Gradients w.r.t. the Output UnitsDownload
28Backpropagation: Computing Gradients w.r.t. Hidden UnitsDownload
29Backpropagation: Computing Gradients w.r.t. ParametersDownload
30Backpropagation: Pseudo codeDownload
31Derivative of the activation functionDownload
32Information content, Entropy & cross entropyDownload
33Recap: Learning Parameters: Guess Work, Gradient DescentDownload
34Contours MapsDownload
35Momentum based Gradient DescentDownload
36Nesterov Accelerated Gradient DescentDownload
37Stochastic And Mini-Batch Gradient DescentDownload
38Tips for Adjusting Learning Rate and MomentumDownload
39Line SearchDownload
40Gradient Descent with Adaptive Learning RateDownload
41Bias Correction in AdamDownload
42Eigenvalues and EigenvectorsDownload
43Linear Algebra : Basic DefinitionsDownload
44Eigenvalue DecompositonDownload
45Principal Component Analysis and its InterpretationsDownload
46PCA : Interpretation 2Download
47PCA : Interpretation 3Download
48PCA : Interpretation 3 (Contd.)Download
49PCA : Practical ExampleDownload
50Singular Value DecompositionDownload
51Introduction to AutoncodersDownload
52Link between PCA and AutoencodersDownload
53Regularization in autoencoders (Motivation)Download
54Denoising AutoencodersDownload
55Sparse AutoencodersDownload
56Contractive AutoencodersDownload
57 Bias and VarianceDownload
58Train error vs Test errorDownload
59Train error vs Test error (Recap)Download
60True error and Model complexityDownload
61L2 regularizationDownload
62Dataset augmentationDownload
63Parameter sharing and tyingDownload
64Adding Noise to the inputsDownload
65Adding Noise to the outputsDownload
66Early stoppingDownload
67Ensemble MethodsDownload
68DropoutDownload
69A quick recap of training deep neural networksDownload
70Unsupervised pre-trainingDownload
71Better activation functionsDownload
72Better initialization strategiesDownload
73Batch NormalizationDownload
74One-hot representations of wordsDownload
75Distributed Representations of wordsDownload
76SVD for learning word representationsDownload
77 SVD for learning word representations (Contd.)Download
78Continuous bag of words modelDownload
79Skip-gram modelDownload
80Skip-gram model (Contd.)Download
81Contrastive estimationDownload
82Hierarchical softmaxDownload
83GloVe representationsDownload
84Evaluating word representationsDownload
85Relation between SVD and Word2VecDownload
86The convolution operationDownload
87Relation between input size, output size and filter sizeDownload
88Convolutional Neural NetworksDownload
89Convolutional Neural Networks (Contd.)Download
90CNNs (success stories on ImageNet)Download
91Image Classification continued (GoogLeNet and ResNet)Download
92Visualizing patches which maximally activate a neuronDownload
93Visualizing filters of a CNNDownload
94Occlusion experimentsDownload
95Finding influence of input pixels using backpropagationDownload
96Guided BackpropagationDownload
97Optimization over imagesDownload
98Create images from embeddingsDownload
99Deep DreamDownload
100Deep ArtDownload
101Fooling Deep Convolutional Neural NetworksDownload
102Sequence Learning ProblemsDownload
103Recurrent Neural NetworksDownload
104Backpropagation through timeDownload
105The problem of Exploding and Vanishing GradientsDownload
106Some Gory DetailsDownload
107Selective Read, Selective Write, Selective Forget - The Whiteboard AnalogyDownload
108Long Short Term Memory(LSTM) and Gated Recurrent Units(GRUs)Download
109How LSTMs avoid the problem of vanishing gradientsDownload
110How LSTMs avoid the problem of vanishing gradients (Contd.)Download
111Introduction to Encoder Decoder ModelsDownload
112Applications of Encoder Decoder modelsDownload
113Attention MechanismDownload
114Attention Mechanism (Contd.)Download
115Attention over imagesDownload
116Hierarchical AttentionDownload

Sl.No Chapter Name English
1Biological NeuronPDF unavailable
2 From Spring to Winter of AIPDF unavailable
3The Deep RevivalPDF unavailable
4From Cats to Convolutional Neural NetworksPDF unavailable
5Faster, higher, strongerPDF unavailable
6The Curious Case of SequencesPDF unavailable
7Beating humans at their own games (literally)PDF unavailable
8 The Madness (2013-)PDF unavailable
9(Need for) SanityPDF unavailable
10Motivation from Biological NeuronsPDF unavailable
11McCulloch Pitts Neuron, Thresholding LogicPDF unavailable
12PerceptronsPDF unavailable
13Error and Error SurfacesPDF unavailable
14Perceptron Learning AlgorithmPDF unavailable
15Proof of Convergence of Perceptron Learning AlgorithmPDF unavailable
16Deep Learning(CS7015): Linearly Separable Boolean FunctionsPDF unavailable
17Deep Learning(CS7015): Representation Power of a Network of PerceptronsPDF unavailable
18Deep Learning(CS7015): Sigmoid NeuronPDF unavailable
19Deep Learning(CS7015): A typical Supervised Machine Learning SetupPDF unavailable
20Deep Learning(CS7015): Learning Parameters: (Infeasible) guess workPDF unavailable
21Deep Learning(CS7015): Learning Parameters: Gradient DescentPDF unavailable
22Deep Learning(CS7015): Representation Power of Multilayer Network of Sigmoid NeuronsPDF unavailable
23Feedforward Neural Networks (a.k.a multilayered network of neurons)PDF unavailable
24Learning Paramters of Feedforward Neural Networks (Intuition)PDF unavailable
25Output functions and Loss functionsPDF unavailable
26Backpropagation (Intuition)PDF unavailable
27Backpropagation: Computing Gradients w.r.t. the Output UnitsPDF unavailable
28Backpropagation: Computing Gradients w.r.t. Hidden UnitsPDF unavailable
29Backpropagation: Computing Gradients w.r.t. ParametersPDF unavailable
30Backpropagation: Pseudo codePDF unavailable
31Derivative of the activation functionPDF unavailable
32Information content, Entropy & cross entropyPDF unavailable
33Recap: Learning Parameters: Guess Work, Gradient DescentPDF unavailable
34Contours MapsPDF unavailable
35Momentum based Gradient DescentPDF unavailable
36Nesterov Accelerated Gradient DescentPDF unavailable
37Stochastic And Mini-Batch Gradient DescentPDF unavailable
38Tips for Adjusting Learning Rate and MomentumPDF unavailable
39Line SearchPDF unavailable
40Gradient Descent with Adaptive Learning RatePDF unavailable
41Bias Correction in AdamPDF unavailable
42Eigenvalues and EigenvectorsPDF unavailable
43Linear Algebra : Basic DefinitionsPDF unavailable
44Eigenvalue DecompositonPDF unavailable
45Principal Component Analysis and its InterpretationsPDF unavailable
46PCA : Interpretation 2PDF unavailable
47PCA : Interpretation 3PDF unavailable
48PCA : Interpretation 3 (Contd.)PDF unavailable
49PCA : Practical ExamplePDF unavailable
50Singular Value DecompositionPDF unavailable
51Introduction to AutoncodersPDF unavailable
52Link between PCA and AutoencodersPDF unavailable
53Regularization in autoencoders (Motivation)PDF unavailable
54Denoising AutoencodersPDF unavailable
55Sparse AutoencodersPDF unavailable
56Contractive AutoencodersPDF unavailable
57 Bias and VariancePDF unavailable
58Train error vs Test errorPDF unavailable
59Train error vs Test error (Recap)PDF unavailable
60True error and Model complexityPDF unavailable
61L2 regularizationPDF unavailable
62Dataset augmentationPDF unavailable
63Parameter sharing and tyingPDF unavailable
64Adding Noise to the inputsPDF unavailable
65Adding Noise to the outputsPDF unavailable
66Early stoppingPDF unavailable
67Ensemble MethodsPDF unavailable
68DropoutPDF unavailable
69A quick recap of training deep neural networksPDF unavailable
70Unsupervised pre-trainingPDF unavailable
71Better activation functionsPDF unavailable
72Better initialization strategiesPDF unavailable
73Batch NormalizationPDF unavailable
74One-hot representations of wordsPDF unavailable
75Distributed Representations of wordsPDF unavailable
76SVD for learning word representationsPDF unavailable
77 SVD for learning word representations (Contd.)PDF unavailable
78Continuous bag of words modelPDF unavailable
79Skip-gram modelPDF unavailable
80Skip-gram model (Contd.)PDF unavailable
81Contrastive estimationPDF unavailable
82Hierarchical softmaxPDF unavailable
83GloVe representationsPDF unavailable
84Evaluating word representationsPDF unavailable
85Relation between SVD and Word2VecPDF unavailable
86The convolution operationPDF unavailable
87Relation between input size, output size and filter sizePDF unavailable
88Convolutional Neural NetworksPDF unavailable
89Convolutional Neural Networks (Contd.)PDF unavailable
90CNNs (success stories on ImageNet)PDF unavailable
91Image Classification continued (GoogLeNet and ResNet)PDF unavailable
92Visualizing patches which maximally activate a neuronPDF unavailable
93Visualizing filters of a CNNPDF unavailable
94Occlusion experimentsPDF unavailable
95Finding influence of input pixels using backpropagationPDF unavailable
96Guided BackpropagationPDF unavailable
97Optimization over imagesPDF unavailable
98Create images from embeddingsPDF unavailable
99Deep DreamPDF unavailable
100Deep ArtPDF unavailable
101Fooling Deep Convolutional Neural NetworksPDF unavailable
102Sequence Learning ProblemsPDF unavailable
103Recurrent Neural NetworksPDF unavailable
104Backpropagation through timePDF unavailable
105The problem of Exploding and Vanishing GradientsPDF unavailable
106Some Gory DetailsPDF unavailable
107Selective Read, Selective Write, Selective Forget - The Whiteboard AnalogyPDF unavailable
108Long Short Term Memory(LSTM) and Gated Recurrent Units(GRUs)PDF unavailable
109How LSTMs avoid the problem of vanishing gradientsPDF unavailable
110How LSTMs avoid the problem of vanishing gradients (Contd.)PDF unavailable
111Introduction to Encoder Decoder ModelsPDF unavailable
112Applications of Encoder Decoder modelsPDF unavailable
113Attention MechanismPDF unavailable
114Attention Mechanism (Contd.)PDF unavailable
115Attention over imagesPDF unavailable
116Hierarchical AttentionPDF unavailable


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