ravi-kr / deeplearning Goto Github PK

Deep Learning:

1. Neural network and its working, perceptron neural network.
2. Activation functions (Threshold, Sigmoid, Relu, Tanh, Softmax)
3. Backpropagation in ANN
4. Bias and Gradient Descent
5. Stochastic Gradient Descent
6. Mini Batch Gradient Descent
7. Keras, Tensorflow, Google Colab
8. Breast Cancer Dataset
9. Iris Dataset
10. Regression based neural network
11. Bias Variance trade-off, Overfitting and Undercutting
12. K-Fold Cross Validation
13. Regularization Lasso and Ridge Regression
14. Dropout
15. Hyperparameter tuning, GridSearchCV
16. Gradient Descent with momentum
17. Adagard Optimizer
18. AdaDelta and RMSprop optimizer
19. Adam optimizer
20. CNN, Feature, Map, Filters
21. Feature Detector, Feature Map
22. Softmax and Crossentropy
23. .flow(X, y)
24. MNIST CNN
25. RNN with LSTM
26. Vanishing and Exploding Gradient
27. LSTM vs GRU
28. Spam Vs Ham using LSTM
29. Iris using LSTM
30. Google Stock Price using LSTM
31. Self (Kohonen) Organizing Map
32. Advanced SOM using K-means clustering
33. Iris using SOM
34. Boltzmann Machine, Boltzmann Distribution, Boltzmann Factor
35. Restricted Boltzmann Machine
36. Contrastive Divergence and Gibbs Sampling in RBM
37. Recommendation System using RBM
38. AutoEncoder
39. Types of AutoEncoder (Overcomplete, Denoising, Stack sparse, Deep, Undercomplete, Contractive, Convolutional, Variational)
40. Movie Recommendation System using AutoEncoder
41. Generative Adversarial Network
42. DCGAN on CIFAR-10
43. Agent and Environment
44. Markov Decision Process
45. Hidden Markov Process
46. Bellman Equation and Q Learning
47. Q Learning using Gym
48. SARSA using Gym

Supervised Learning
1. Artificial Neural Network (ANN)
2. Convolutional Neural Network (CNN)
3. Recurrent Neural Network (RNN)

Unsupervised Learning
1. Self Organizing Map (SOM)
2. Boltzmann Machine
3. AutoEncoders

Reinforcement Learning
1. Q Learning
2. SARSA