Domain Neighborhood

Probability

Uncertainty made precise: events, random variables, expectations, and the distributions that models learn.

6 concepts6 published6 demos

Recommended Route

This sequence is ordered for learning rather than inventory: lower difficulty, fewer prerequisites, and more central concepts come first.

  1. 01
    Probability Basics

    Events are subsets of a sample space, and probabilities obey a few axioms; from there you get conditional probability, independence, and Bayes' rule.

    12 mincodedemoentry point

    Entry point: build the first mental model here.

  2. 02
    Distributions

    A distribution is the law of a random variable: it says how probability mass or density lands on the values the variable can take.

    15 mincodedemoafter Random Variables

    Why this follows: both pages keep the probability thread active.

  3. 03
    Random Variables

    A random variable is a function from outcomes to numbers; its distribution lets you compute expectations, variances, and likelihoods.

    14 mincodedemoafter Probability Basics

    Why this follows: both pages keep the probability thread active.

  4. 04
    Cross-Entropy

    Cross-entropy is the target-weighted surprise of a model distribution; in deep learning it is the bridge from likelihood to a differentiable training loss.

    16 mincodedemoafter Maximum Likelihood

    Why this follows: both pages keep the probability thread active.

  5. 05
    Maximum Likelihood

    Maximum likelihood fits parameters by making the observed data most probable; for classifiers it becomes negative log-likelihood, cross-entropy, and a KL fit to the empirical distribution.

    18 mincodedemoafter Distributions, Derivatives

    Why this follows: both pages keep the probability / information theory thread active.

  6. 06
    Bayesian Inference

    Bayesian inference updates a prior distribution over unknowns into a posterior by multiplying by the likelihood and normalizing.

    17 mincodedemoafter Distributions, Maximum Likelihood

    Why this follows: Bayesian Inference uses Maximum Likelihood directly.

All Published Notebooks

Browse the territory.