Mathematical Notation

Why Do We Need Mathematical Notation?

Imagine saying:

Take the student's study hours,
multiply them by 10,
and use the result as a prediction.

Mathematics can express the same idea much more simply:

prediction = study_hours × 10

This becomes especially important in AI because AI models perform thousands or millions of mathematical calculations.

Mathematical notation gives us a short and standard way to describe those calculations.

Numbers and Variables

You already learned that a variable is a name that represents a value. Mathematical notation uses variables heavily.

x = 5
y = 10

Here:

• x represents the number 5.
• y represents the number 10.

We can then perform calculations using those variables.

x + y

5 + 10

= 15

In AI, variables can represent things such as age, price, temperature, image values, or model parameters.

Basic Mathematical Symbols

You will see these symbols constantly when learning AI and machine learning.

+    Addition
-    Subtraction
×    Multiplication
÷    Division
=    Equal to

For example:

x = 5
y = 2

x + y = 7
x - y = 3
x × y = 10
x ÷ y = 2.5

These basic operations are the foundation for much more complicated calculations used by AI models.

The Equal Sign (=)

The equal sign means that the value on the left and the value on the right represent the same value.

x = 10

This means:

x has the value 10

Another example:

prediction = 50

This means the variable prediction currently has the value 50.

You will see this notation everywhere in machine learning formulas.

Exponents

An exponent tells us to multiply a number by itself a certain number of times.

For example:

2² = 2 × 2 = 4

Another example:

3³ = 3 × 3 × 3 = 27

Exponents appear in many areas of AI and mathematics. For example, they are used in formulas involving probability, neural networks, and mathematical transformations.

Variables Used in AI

AI uses letters to represent different types of information. The exact meaning depends on the formula.

x = input data
y = actual answer
ŷ = predicted answer
w = model weight
b = bias

For example, suppose an AI model predicts a house price.

x = house size
y = actual house price
ŷ = predicted house price

The important thing is that these letters are not magic. They are simply short names for values.

A Simple AI Formula

Here is a very simple formula that looks like something you will see later in machine learning:

ŷ = w × x + b

We can read this as:

Prediction = weight × input + bias

Suppose:

x = 5
w = 2
b = 3

Substitute those values into the formula:

ŷ = 2 × 5 + 3

ŷ = 10 + 3

ŷ = 13

So the model's prediction is 13.

This is a very simple example, but the same basic idea is used in real machine learning models with many more variables and much more complicated mathematics.

Function Notation

Another notation you will frequently see in AI is a function.

A function takes an input and produces an output.

f(x) = 2x + 1

If:

x = 5

then:

f(5) = 2(5) + 1

f(5) = 10 + 1

f(5) = 11

So the function takes 5 as input and produces 11 as output.

AI uses functions to transform inputs into outputs. Neural networks are built from many mathematical functions working together.

Notation You Will See Later

As you continue learning AI mathematics, you will see notation that looks more complicated.

x       → input
y       → actual answer
ŷ       → predicted answer
w       → weight
b       → bias
f(x)    → function
Σ       → sum
∂       → partial derivative
∇       → gradient

Do not try to memorize everything right now. You will learn each symbol when we reach the topic where it is needed.

For example, the symbol Σ will become important when we learn how AI calculates the total of many values.

Why Mathematical Notation Matters in AI

AI models can contain many calculations. Writing every calculation using normal sentences would become extremely difficult to read.

Mathematical notation gives researchers and developers a common language for describing those calculations.

Real-World Data
      ↓
Represent Data With Numbers
      ↓
Use Variables
      ↓
Apply Mathematical Operations
      ↓
Build Mathematical Formula
      ↓
AI Model
      ↓
Prediction

This is why learning mathematical notation is useful. It allows you to understand what an AI model is actually doing instead of treating the model like a black box.