[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
- Practical Cases
- Ref & Glossary

[New] Concise and Practical AI/ML

...

Calculus

Explore

Calculus

What are Involved?

Calculus by Newton-Leibniz, notably derivation. The Newton notation (use quote ‘) is neat and fast but harder to imagine, this book uses Leibniz notation (use d/dx) for solving the dynamic programming formula of backpropagation as the chain rule can be seen more clearly.

The

⁠

is read as derivative of f, the process of finding the derivative of a function is call derivation.

Derivative of a Function

Derivative of a function f is a function t which has results as the rates of change at all points of function f. Each result of t at x can be used as coefficient to draw a tangent line to the function f at x.

For example,

⁠

, the derivative of f is:

⁠

Basic Calculus: Derivation

Important Concepts

Variables

When solving derivation, there can be 1 or multiple variables.

With-Respect-To (WRT)

With-respect-to a variable means keeping that variable in solving derivation, the rest of variables are not related and can be thrown out of the formula.