Skip to main content
ModelTerms

Foundations · beginner

Machine Learning (ML)

Machine learning is the branch of AI in which models learn patterns from data instead of being explicitly programmed. The training process adjusts model parameters to reduce error on examples.

Explanation

Traditional software is written by humans line by line. A machine learning model, in contrast, is trained: you feed it many examples (input then desired output), let it guess, measure how wrong the guesses are, and adjust the model's internal numbers to reduce that error. Repeat billions of times and the model gets useful.

The three classic flavors are supervised learning (each example has a label), unsupervised learning (find structure without labels), and reinforcement learning (learn by trial and reward). Modern LLMs combine all three across their lifecycle.

Almost every "AI" headline since 2015 is really about machine learning, and specifically about deep learning — ML with very large neural networks.

Examples

  • A spam classifier learning what spam looks like from labeled examples (supervised).
  • Clustering customers into segments without preset categories (unsupervised).
  • A game-playing AI improving through self-play (reinforcement learning).

Frequently asked

What is Machine Learning?

Machine learning is the branch of AI in which models learn patterns from data instead of being explicitly programmed. The training process adjusts model parameters to reduce error on examples.

What is an example of machine learning?

A spam classifier learning what spam looks like from labeled examples (supervised).

How is Machine Learning related to Artificial Intelligence?

Machine Learning and Artificial Intelligence are both foundations concepts. Artificial intelligence is the field of computer science that builds systems capable of tasks normally thought to require human intelligence, such as understanding language, recognizing images, or making decisions.

Is Machine Learning considered beginner?

Machine Learning is generally considered beginner-level material in the AI and LLM space.

Artificial IntelligenceFoundations

Artificial intelligence is the field of computer science that builds systems capable of tasks normally thought to require human intelligence, such as understanding language, recognizing images, or making decisions.

Deep LearningFoundations

Deep learning is machine learning using neural networks with many layers ("deep" = many layers). It powers nearly every recent breakthrough in AI, including LLMs and image generators.

Neural NetworkFoundations

A neural network is a stack of simple mathematical units ("neurons") that learn to transform inputs into outputs by adjusting numeric weights during training.

PretrainingTraining

Pretraining is the initial training phase where an LLM learns to predict the next token on trillions of tokens of general text. It produces a base model that can be adapted later.

Fine-tuningTraining

Fine-tuning continues training a pretrained model on a smaller, task-specific dataset, adjusting its weights to specialize behavior or knowledge.

Side-by-side comparisons

Sources