AIExplainer
Machine Learning Intermediate 2 min read

What is generalization?

The ability of a model to apply learned knowledge to new, unseen situations

Generalization refers to the capacity of an artificial intelligence or machine learning model to take what it has learned from a set of training data and apply it to new, different situations that it has not encountered before. This is a key aspect of creating models that are useful in real-world scenarios, where the data is often varied and unpredictable.

Think of generalization like a child learning to recognize dogs. At first, the child may only be shown pictures of their own family's dog, but as they learn and generalize, they become able to recognize other dogs they have never seen before as also being dogs.

Self-driving cars rely heavily on generalization to navigate roads they have never been on before. The cars are trained on a vast amount of data from various roads and conditions, and then they use this training to generalize and make decisions in new, unseen situations.

Generalization is used in all areas of machine learning and artificial intelligence, from image recognition and natural language processing to decision-making systems and predictive modeling. It is crucial for creating models that can perform well on a wide range of tasks and data sets.

One common misconception is that generalization is the same as memorization. However, memorization involves simply recalling learned information, whereas generalization involves applying learned knowledge to new situations.

The concept of generalization has been around since the early days of machine learning and artificial intelligence. It has evolved over time as new techniques and algorithms have been developed to improve the ability of models to generalize.

abstraction induction extrapolation

Three products for different needs — explore what’s relevant to you.