Learn Machine Learning

Contents

1. Basics

1. Types of Machine Learning
   • Supervised Machine Learning
   • Unsupervised Machine Learning
   • Reinforcement Learning
2. Regression
3. Classification
4. Resources

2. Neural Networks

1. Recurrent Neural Network (RNN) 1.1 Long Short Term Network (LSTM)

3. Deep Learning

1. Basics

   1.1 The Perceptron

   • Layers (Input / Hidden / Output)
   • Standardization
   • Normalization
     • Min-Max Normalization
   • Feature Scaling

2. Activation Function

   • Sigmoid
     • Hard Sigmoid
   • ReLU (Rectified Linear Unit)
     • Leaky ReLU
     • PReLU (Parametric ReLU)
   • Softmax
   • Tanh (Hyperbolic Tangent)
   • Linear (Identity)
   • ELU (Exponential Linear Unit)
   • SELU (Scaled Exponential Linear Unit)
   • Swish
     • Hard Swish
   • GELU (Gaussian Error Linear Unit)
   • Maxout
   • Softplus

3. Loss Function

4. Optimizers

5. Forward Propogation

6. Backward Propogation

7. Pooling

8. Non Linearity

9. Hyperparameter Tuning

10. Resources