Machine learning

Machine learning is an approach in which a model’s behavior is shaped by finding patterns in data or experience rather than only by fixed task rules.

Plan for this page

Understand one concept in plain language and connect it to nearby ideas.

You will leave with: During training, a learning procedure adjusts a model so that its outputs better fit an objective measured on examples or interactions. The resulting behavior depends on the data, representation, objective, method, and evaluation—not on the word “learning” alone.
Time: 3–8 min
Before you begin: No prerequisite. Keep one real example in mind.
Do this now: Read the explanation, then compare the example with the common misunderstanding.

Prepared next stepLearn how data shapes behavior

Machine learningMachine learning is an approach in which a model’s behavior is shaped by finding patterns in data or experience rather than only by fixed task rules.

Deep learning
Training
Dataset
Generalization

Plain explanation

During training, a learning procedure adjusts a model so that its outputs better fit an objective measured on examples or interactions. The resulting behavior depends on the data, representation, objective, method, and evaluation—not on the word “learning” alone.

Example

A spam filter can learn patterns from messages labeled spam or not spam, then estimate the class of a new message.

Why it matters

Many current AI systems use machine learning, so their behavior cannot be understood only by reading a short list of rules. Data quality, evaluation, distribution change, and human decisions all affect results.

Common misunderstanding

Misconception: the system learns exactly as a person does. Correction: machine learning is an optimization process with specified data and objectives, not proof of human-like comprehension.

Related concepts

Follow relationships, not only the alphabet

Deep learningDeep learning is machine learning built with neural networks containing multiple layers of learned transformations.TrainingTraining is the process of adjusting a model to improve performance on an objective using data, feedback, or interaction.DatasetA dataset is an organized collection of examples or records used for training, evaluation, analysis, or system operation.GeneralizationGeneralization is a model’s ability to perform usefully on relevant examples or conditions not seen during training.

Learn how data shapes behavior

Sources and scope

What supports this object

Machine Learning GlossaryGoogle for Developers

Technical glossary for machine-learning concepts; terminology can vary across research fields and production systems.

Open source

Loading page content...

…