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
        • Normalization
        • icon picker
          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
/
/
Regularization
Share
Explore

Regularization

Drop-out Technique
Regularization is the punishment of changes set to loss value to avoid params (weights and biases) change to much, leave space of possible values of params for unknown data, better for generalizing.
Regularisation technique is used to limit the weights and avoid them saturate into a large range and no possible to fit (match) with the inputs. It is done by using a portion of loss to punish (reduce) the changes to weights.

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.