Concepts

Machine learning

5 min readbeginnerUpdated 28 Sept 2026
1 · In one line

Machine learning trains software on data so it can find patterns and make useful predictions or generate content for new inputs.

1 · What it is

Machine learning builds software by training it on data. The result is a model, a structure plus learned numbers called parameters that together produce predictions. One widely used textbook sets a single test for the algorithm behind it: it must be “able to learn from data.”

In supervised learning, each example contains two parts: features, the information given to the model, and a label, the answer it should predict. Training changes the model to reduce a measured error called loss. Evaluation then uses examples kept out of training to check whether the learned relationship generalises.

Once accepted, the model can receive a new input and produce a prediction. That stage is inference. Other forms of machine learning learn differently: unsupervised methods search for structure without labels, and generative models learn to produce new content. Reinforcement learning instead improves through rewards or penalties for the actions it takes in an environment.

2 · Why it exists

Machine learning helps when useful relationships can be learned from examples.

Too many rulesSome relationships, such as those between weather conditions and rainfall, are difficult to express as a complete hand-written program.
New casesThe finished model must work on examples that were not in its training set.
Hidden patternsUnsupervised learning can find meaningful groupings even when the dataset has no supplied answers.
3 · How it works

Separate learning the pattern from using it.

QUESTION: HOW DOES DATA BECOME A NEW PREDICTION?TRAIN FIRSTUSE: APPLY THE PATTERN Training examplesAdjust the modelHeld-out examplesSaved model New inputSaved modelPrediction features + known labelspredict → loss → updatecompare with answerslearned relationship features, no answerparameters stay fixednumber or category evaluation sends failures back to training 1 2 3 4 Training changes the model. Inference sends a new input through the saved model.
  1. 1 · collectGather examples whose features contain information relevant to the result you want.
  2. 2 · trainA training algorithm adjusts the model to reduce the difference between its predictions and the known answers.
  3. 3 · evaluateRun the trained model on examples it never saw, and check its answers against the real ones.
  4. 4 · inferGive the accepted model a new input; producing its prediction is called inference.

Training changes the model; inference uses the trained model without repeating that training for each request.

4 · Where it's used
WhoWhat they askWhat it works with
Email service“Is this new message spam?”Words, sender details and labels from earlier messages
Energy planner“How much electricity will this building use tomorrow?”Past usage, weather and building features
Music app“Which song might this listener enjoy next?”Listening patterns and item information
Factory team“Does this sensor pattern suggest a fault?”Equipment readings and previous outcomes
5 · What it solves, and what it doesn't
solves
  • It can predict a number, such as rainfall or travel time, from relevant input data.
  • It can classify an input, such as deciding whether an email belongs to the spam category.
  • It can discover groups in unlabeled data through unsupervised learning.
  • It can generate new content when trained as a generative model.
doesn't solve
  • Machine learning does not remove the need to evaluate how well the trained model works.
  • More examples do not help if the data lacks the range or quality needed for the intended setting.
  • Success on training examples does not guarantee good predictions on unfamiliar examples.
  • A model may need more rounds of training and testing before it is ready for real use.
6 · Go deeper

Sources used

This explainer is written in original language. The links below support its factual claims.

  1. docsWhat is Machine Learning?, Google for Developers · read 27 Sept 2026
  2. docsSupervised Learning, Google for Developers · read 27 Sept 2026
  3. docsMachine Learning Glossary: ML Fundamentals, Google for Developers · read 27 Sept 2026
  4. officialMachine Learning - Glossary, National Institute of Standards and Technology · read 27 Sept 2026
  5. docsEndpoints for inference in production, Microsoft Learn · read 27 Sept 2026
  6. docsCross-validation: evaluating estimator performance, scikit-learn · read 27 Sept 2026
  7. paperDeep Learning, Chapter 5: Machine Learning Basics, Goodfellow, Bengio and Courville, MIT Press 2016 · read 27 Sept 2026