padh.ai - Deep Learning

Code and Documents related to Deep Learning Course at padh.ai

• Practical
• Theory
• Complete
• Incomplete

S.no	Module	Theory/Practical	Status	Notes
1	Python Basics	Practical		Here
2	6Jars and Expert Systems	Theory		Here
3	Linear Algebra Basics	Theory		Here
4	Python Basics 2	Practical		Here
5	MP Neuron	Theory		Here
6	Perceptron Model	Theory		Here
7	MP Neuron and Perceptron Practical	Practical		Here
8	Sigmoid Neuron	Theory		Here
9	Contest 1	Practical		Here
10	Sigmoid Neuron using Python	Practical		Here
11	Probability	Theory		Here
12	Information Theory & Cross Entropy	Theory		Here
13	Contest 2	Practical		Here
14	Representation Power of Function	Theory		Here
15	Deep Neural Networks	Theory		Here
16	DNNs using Python	Practical		Here
17	Backpropagation	Theory		Here
18	Backpropagation using Python	Practical		Here
19	Backpropagation 2	Theory		Here
20	Backpropagating - the full version using Python	Practical		Here
21	Optimisation Algorithms Theory 1	Theory		Here
22	Optimisation Algorithms Theory 2	Theory		Here
23	Optimisation Algorithms Practical	Practical		Here
24	Activation Functions & Initialisation Methods Theory	Theory		Here
25	Activation Functions & Initialisation Methods Practical	Practical		Here
26	Regularization Theory	Theory		Here
27	Regularization Practical	Practical		Here
28	Basics of Pytorch	Practical		Here
29	FNNs using Pytorch	Practical		Here
30	The Convolution Operation	Theory		Here
31	Convolution to Neural Networks	Theory		Here
32	CNNs in Pytorch	Practical		Here
33	CNN Architectures 1	Theory		Here
34	CNN Architectures 2	Theory		Here
35	Building CNNs	Practical		Here
36	Visualising CNNs	Practical		Here
37	Visualising CNNs in Python	Practical		Here
38	Batch Normalization and Dropout	Theory		Here
39	Batch Normalization and Dropout using Python	Practical		Here
40	Hypermeter Tuning and MLFlow	Practical		Here
41	Sequence Learning Problems	Theory		Here
42	Recurrent Neural Networks	Theory		Here
43	Vanishing and Exploding Gradients	Theory		Here
44	LSTMs and GRUs	Theory		Here
45	Sequence Models in Pytorch	Practical		Here
46	Addressing the problem of vanishing and exploding gradients	Theory		Here
47	Batching for Sequence Models in Pytorch	Practical		Here
48	Neural Encoders and Decoders	Theory		Here
49	Attention Mechanism	Theory		Here
50	Encoder Decoder Models and Attention Mechanism using PyTorch	Practical		Here
51	RCNN	Theory		Here
52	YOLO	Theory		Here

Note : Some links might not work. They are a work in progress.

Additional Resources for better understanding:

Topic	Source
LSTMs solving vanishing gradient problem	Link
Using nn.init methods for initialising weights in Pytorch	Link
Long Short-Term Memory: From Zero to Hero with PyTorch	Link
Understanding the return type of nn.LSTM in Pytorch	Link
Operating with variable length sequences for batching using packing in Pytorch	Link
Stackoverflow packing sequences	Link
Backpropogation in CNN	Link 1 , Link 2
Utility of 1*1 convolutions	Link
Illustrated Transformer	Link
Attention is all you need; Attentional Neural Network Models, Łukasz Kaiser , Masterclass	Link