Distributions

What

A probability distribution describes all possible values a random variable can take and how likely each is.

Key distributions

Discrete

DistributionWhat it modelsExample
BernoulliSingle yes/no trialCoin flip, spam/not-spam
BinomialCount of successes in n trialsHow many emails are spam out of 100
CategoricalOne of k classesWhich digit (0-9) an image shows
PoissonCount of events in an intervalNumber of requests per second

Continuous

DistributionWhat it modelsExample
Normal (Gaussian)Bell curve, most commonHeights, measurement errors, weight initialization
UniformEqual probability everywhereRandom number generation
ExponentialTime between eventsTime between server failures

Why it matters

  • Normal distribution: weight initialization, batch normalization, noise injection
  • Softmax output: categorical distribution over classes
  • Generative models: learn to sample from the data distribution
  • Central Limit Theorem: averages of anything → normal distribution (why it’s everywhere)

Key properties

  • PDF/PMF: the function that gives probability (density) at each value
  • CDF: cumulative — P(X ≤ x)
  • Parameters: normal has μ (mean) and σ (std dev), Bernoulli has p