PadhAI-Deep Learning Course

This article serves as the index page for the articles corresponding to different modules of the Deep Learning course.

1. Expert Systems
2. 6 Jars of Machine Learning
3. Vectors and Matrices
4. MP Neuron
5. Perceptron
6. Sigmoid Neuron and Gradient Descent Part 1
7. Sigmoid Neuron and Gradient Descent Part 2
8. Mathematics behind the parameters update rule
9. Basics: Probability Theory
10. Information Theory
11. Sigmoid Neuron and Cross-Entropy
12. Representation Power of Functions
13. Feedforward Neural Networks Part 1
14. Feedforward Neural Networks Part 2
15. Backpropagation(light math)
16. Backpropagation(vectorized)
17. Optimization Algorithms(Part 1)
18. Optimization Algorithms(Part 2)
19. Activation Functions and Initialization Methods
20. Bias-variance Tradeoff
21. Regularization Methods
22. The Convolutional Operation
23. Convolutional Neural Networks
24. CNN Architectures
25. CNN Architectures — Part 2
26. Visualizing CNNs
27. Batch Normalization
28. Dropout Technique
29. Sequence Learning Problems
30. How to model sequence learning problems?
31. Data and Tasks for Sequence Classification
32. Data and Tasks for Sequence Labeling
33. Data Modeling for Recurrent Neural Networks
34. The loss function for Recurrent Neural Networks
35. Learning Algorithm - Recurrent Neural Networks
36. Evaluation metrics for sequence-based tasks
37. Vanishing and Exploding gradients
38. The whiteboard analogy to deal with vanishing and exploding gradients
39. LSTMs and GRUs

References: PadhAI