Skip to content
[New] Concise and Practical AI/ML
  • Pages
    • Preface
    • icon picker
      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
    • Practical Cases
    • Ref & Glossary
[New] Concise and Practical AI/ML
/
Artificial Intelligence
Share
Explore

Artificial Intelligence

Concepts
High-level Intelligence

Formula

AI = Genetics + ML

Genetics

Genetics are about the known data and known processes. Genetics are classic or popular algorithms including the genetics algorithm itself, and known data. ML part is the best with combinatory models. Genetics is mostly not mention in this book, and only about machine learning (ML).
The formula could be AI = Instincts + ML, but that would be not enough, using the word ‘Instincts’ (ready-to-use instincts) will be missing the evolution process which upgrades intelligence and allow re-learning of things for creativity.
Points of genetics:
Known data, known processes
Mechanism for evolving (for better data + processes, for relearning for creativity)
Guardrail, ethical rules

ML (Machine Learning)

ML is how AI learns more about data and new processes.
Formula of machine learning:
ML = SL + RL + UL
SL (supervised learning) is learning with output known
RL (reinforcement learning) is learning with output partially known
UL (unsupervised learning) is learning with output not-known

AI Evolution

Logic-based AI
Expert system
Neural network
Quantum RL

Bio and AI

Cerebrum is similar to CPU/GPU/NPU/Mem for processing and storing live data. Cerebellum & core parts are similar to Storage. Human cerebrum can’t fit all the data in cerebellum, just as Mem can’t fit all data from Storage.
Some concepts:
Remember is storing info to (1)Mem then (2)Storage.
Recall is taking info out from (2)Storage back to (1)Mem.
Thinking of is working with info in Mem.
Knowing is recallable to think.
Action is the result of thinking with known info.
⁠

Formula
AI = Genetics + ML
Genetics
ML (Machine Learning)
AI Evolution
Bio and AI
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.