MACHINE LEARNING • LESSON 2

Input → Model → Output

One of the simplest ways to understand a Machine Learning system is to think about three parts: what goes in, what processes it, and what comes out.

INPUT Information

Data given to the model.

MODEL Learned Pattern

Uses what was learned from data.

OUTPUT Prediction

The result produced by the model.

01

What Is the Input?

The input is the information we give to a trained model when we want it to produce an output.

What the input contains depends on the problem we are trying to solve.

HOUSE PRICE House size

For example, 1,500 square feet.

SPAM DETECTION Email information

For example, words and sender information.

02

What Is the Model?

The model is the part of the system that represents what was learned from training data.

Once trained, the model can take new input and produce an output.

MODEL Learned relationship between input and output

The model is not simply the original training data. It is the result of a learning process applied to that data.

03

What Is the Output?

The output is the result produced by the model after it receives input.

PREDICTION $420,000

Predicted house price.

CLASSIFICATION Spam

Predicted category.

RECOMMENDATION Product A

Recommended item.

04

The House Price Example

Let's connect the three parts to the house-price problem from Lesson 1.

INPUT 1,500 sq ft

Information about the new house.

MODEL Learned relationship

Uses the relationship learned from previous examples.

OUTPUT $420,000

Predicted house price.

05

Training Happens Before This Flow

There is an important detail here. The simple Input → Model → Output flow assumes that the model already exists.

TRAINING DATA Examples
TRAINING Learn patterns
MODEL Ready to use

After training, we can provide new input to the model and receive an output.

TRAINING Learn

Training data → model

PREDICTION Use

New input → output

06

Input Does Not Mean "Everything About the Object"

The input contains the information we choose to provide to the model.

A house has many properties, but our simple model might only receive its size.

REAL HOUSE Many properties

Size, location, age, bedrooms, condition, and more.

MODEL INPUT House size

Only the information provided to this particular model.

07

Different Problems Have Different Outputs

Input → Model → Output is a general structure. The meaning of the output depends on the problem.

REGRESSION Number

Example: predict house price.

CLASSIFICATION Category

Example: spam or not spam.

RECOMMENDATION Item / Ranking

Example: recommend a product.

KEY IDEA

Input → Model → Output

The input provides information. The trained model applies what it learned. The output is the result produced for that input.

QUICK CHECK

Identify the Three Parts

House price prediction

Input: house size → Model: learned relationship → Output: predicted price.

Spam detection

Input: email information → Model: learned pattern → Output: spam or not spam.

NEXT TOPIC

Real-World Problem → ML Problem

Next, we'll take a real-world problem and see how we transform it into a problem that a Machine Learning system can work with.