Topics Covered

I. Perceptron

1. Perceptron
2. Geometric Intuition

II. Multi Layer Perceptron

1. MLP Notation
2. MLP Intuition
3. MLP Example
4. Change Architecture
5. Change Architecture II
6. MLP Forward Propagation
7. MLP Forward Propagation II
8. MLP Forward Propagation III
9. MLP Forward Propagation IV
10. MLP Backpropagation
11. MLP Backpropagation II
12. MLP Backpropagation III
13. MLP Backpropagation (Classification)
14. Backpropagation Intuition (Loss Function-Gradient)
15. Backpropagation Intuition (Derivative-Minima)
16. Backpropagation Intuition
17. Effect of Learning Rate

III. Improve Performance

1. Loss Function
2. Loss Function (MSE)
3. Loss Function (MAE and Huber)
4. Loss Function (Binary Cross Entropy)
5. Loss Function (Categorical Cross Entropy)
6. Memoization
7. Gradient Descent I
8. Gradient Descent II
9. Vanishing Gradient Problem
10. Solve Vanishing Gradient Problem
11. Improve Neural Network
12. Problem with Neural Network
13. Early Stopping
14. Normalizing Input
15. Dropout Layer I
16. Dropout Layer II
17. Regularization
18. Regularization Intuition
19. Activation Function
20. Activation Function (Sigmoid)
21. Activation Function (Tanh)
22. Activation Function (ReLu)
23. Activation Function (Dying ReLu Problem)
24. Activation Function (Relu Variation I)
25. Activation Function (Relu Variation II)
26. Weight Initialization Technique
27. Weight Initialization (Zero Initialization I)
28. Weight Initialization (Zero Initialization II)
29. Weight Initialization (Non-Zero Constant)
30. Weight Initialization (Random Initialization-small I)
31. Weight Initialization (Random Initialization-small II)
32. Weight Initialization (Random Initialization-large I)
33. Weight Initialization (Random Initialization-large II)
34. Weight Initialization
35. Batch Normalization I
36. Batch Normalization II
37. Batch Normalization III
38. Understanding Graph
39. Exponantially Weighted Moving Average
40. Exponantially Weighted Moving Average (Intuition)
41. Optimizers
42. Optimizers (Momentum)
43. Optimizers (NAG)
44. Optimizers (AdaGrad)
45. Optimizers (AdaGrad Intuition)
46. Optimizers (RMSProp)
47. Optimizers (Adam)
48. Functional API
49. Functional API (Topology)
50. Functional API (Topology II)

IV. Convolutional Neural Network

1. Convolution Operation I
2. Convolution Operation II
3. Padding
4. Stride
5. Pooling
6. Pooling Code and Advantage
7. Pooling Disadvantage
8. CNN Architecture
9. LeNet-5
10. CNN vs ANN
11. Backpropagation in CNN I
12. Backpropagation in CNN II
13. Backpropagation in CNN III
14. Backpropagation in CNN IV
15. Backpropagation in CNN V
16. Pretrained Model in CNN
17. Transfer Learning in CNN-Feature Extraction
18. Feature Extraction Code
19. Transfer Learning in CNN-Fine Tuning
20. Fine Tuning Code

V. Recurrent Neural Network

1. RNN Introduction
2. Data feeding in RNN
3. RNN Intuition
4. RNN Representation
5. Types of RNN I
6. Types of RNN II
7. RNN Forward Propagation
8. RNN Backpropagation I
9. RNN Backpropagation II
10. RNN Backpropagation III
11. Problem with RNN I
12. Problem with RNN II

Research Papers

1. (1957) Frank Rosenblatt - Perceptron
2. (1959) Receptice Field Experimernt used in CNN
3. (1969) Marvin Minsky - First AI winter
4. (1980) Geoff Hinton - Learning representation using back propogation error
5. (1981) Fukushima Miyake - Early CNN
6. (1989) Yan LeCun - Handwritten Digit Recognition
7. (2006) Geoff Hinton - Deep belief network
8. (2012) Imagenet Classification with Deep CNN
9. (2014) Dropout Discovery
10. (2014) GAN Discovery
11. (2016) Regularization for Deep Learning

We appreciate your interest and contributions to the EnthuAi repository