Skip to content
[New] Concise and Practical AI/ML
  • Pages
    • Preface
    • Artificial Intelligence
      • Concepts
      • High-level Intelligence
    • Maths for ML
      • Calculus
      • Algebra
    • Machine Learning
      • History of ML
      • ML Models
        • ML Model is Better
        • How a Model Learns
        • Boosted vs Combinatory
      • Neuralnet
        • Neuron
          • Types of Neurons
        • Layers
        • Neuralnet Alphabet
        • Heuristic Hyperparams
      • Feedforward
        • Input Separation
      • Backprop
        • Activation Functions
        • Loss Functions
        • Gradient Descent
        • Optimizers
      • Design Techniques
        • icon picker
          Normalization
        • Regularization
          • Drop-out Technique
        • Concatenation
        • Overfitting & Underfitting
        • Explosion & Vanishing
      • Engineering Techniques
    • Methods of ML
      • Supervised Learning
        • Regression
        • Classification
      • Reinforcement Learning
        • Concepts
        • Bellman Equation
        • Q-table
        • Q-network
        • Learning Tactics
          • Policy Network
      • Unsupervised Learning
        • Some Applications
      • Other Methods
    • Practical Cases
    • Ref & Glossary
[New] Concise and Practical AI/ML
/
/
Normalization
Share
Explore

Normalization

Importance

Normalisation is the technique in ML to make input values or input values to a hidden layer closer so they have similar meanings, and also it’s required for the network to learn because a network can’t learn infinite range, ie. without normalisation.
Normalization is a must in neuralnet, inputs must be normalized, to reduce the range of values of inputs. If leaving inputs unnormalized, the params must fit to the infinity of possibilities of input values and that’s impossible, and the network can’t be trained.


Importance
Gallery
 
Want to print your doc?
This is not the way.
Try clicking the ··· in the right corner or using a keyboard shortcut (
CtrlP
) instead.