Glossary · Artificial Intelligence

What is Overfitting?

When a model memorises its training data so closely that it performs poorly on new data.

In more detail

It is like a student who memorises last year’s answers word for word and fails when the questions change. More data, simpler models and validation help prevent it.

Example

A model with 99% training accuracy but 60% accuracy on new data is overfitting.

Learn it properlyAI vs Machine Learning vs Deep Learning: What Is the Difference?9 min lesson · Artificial Intelligence

Related terms

Full glossary

AI AgentAn AI system that can plan steps and use tools — search, code, apps — to complete a task with less step-by-step instruction.Artificial Intelligence (AI)Software that learns patterns from data and uses them to make predictions, decisions or new content.Bias (in AI)Systematic unfairness in AI output, usually inherited from imbalanced or historical training data.Context WindowThe maximum amount of text a language model can consider at one time.Deep LearningMachine learning that uses neural networks with many layers, especially good for images, audio and language.Fine-TuningFurther training a pre-trained model on a smaller, specific dataset to adapt it to a task or style.