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
        • 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
    • icon picker
      Practical Cases
    • Ref & Glossary
[New] Concise and Practical AI/ML
/
Practical Cases
Share
Explore

Practical Cases

Classic

Classification

Regression

Pattern Learning

Image Classification
Object Detection
Optical Character Recognition (OCR)
Segmentation
Transformation
Image-to-Image

Sequence Learning

Natural Language Processing (NLP)
Voice Recognition
Sequence to Sequence
Text Translation

Algorithm Approximator

Each algorithm can be understood as a function. A network is also a function thus a network can learn to work in place of an algorithm, however, neuralnet will return roughly results instead of exact results thus it can be called algorithm approximator.

The Benefit

Using neuralnet as algorithm approximator has a big benefit as:
Classic algorithm takes intensive amount of time to give output
Neuralnet takes a tiny amount to time for a feed to give output

The Drawback

Neuralnet as algorithm approximator has drawback too
Classic algorithm may/or may not give exact results
Neuralnet always gives approximate results, never exact.

Generative

GAN

Classic
Classification
Regression
Pattern Learning
Sequence Learning
Algorithm Approximator
The Benefit
The Drawback
Generative
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.