AI engineering glossary · Probability
What is categorical distribution?
Categorical distribution: The distribution of a single trial with several possible outcomes, each having its own probability, with the probabilities summing to 1. It generalises the Bernoulli distribution and is the output of a softmax classifier.
Categorical distribution: an example
A model gives probabilities 0.7, 0.2 and 0.1 for the classes cat, dog and bird for one image.
Related terms
- Multinomial distribution
- Softmax function
- Bernoulli distribution
More Probability terms
- Central limit theorem
- Chain rule of probability
- Chebyshev's inequality
- Classical probability
- Cluster sampling
- Combination
- Complement rule
- Conditional distribution
Where you learn it
Categorical distribution is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.