Olasılıksal Makine Öğrenmesi

Probabilistic Prediction

1. Probabilistic PredictionOutputs as distributions: predicting uncertainty instead of pretending certainty.1–2 sa
2. The Multivariate GaussianMean vector and covariance matrix: the ellipse geometry behind GDA, mixtures, Gaussian processes, Kalman filters, and diffusion.1–2 sa
3. Density Estimation: Histograms and KernelsEstimating a distribution from samples, and the bandwidth choice that decides between spiky and oversmoothed.1–2 sa

Fitting

1. LikelihoodHow probable is the data under these parameters? The question that fits models.1–2 sa
2. Maximum Likelihood EstimationFitting as hill-climbing on likelihood: the parameters that make data most probable win.1–2 sa
3. MAP and PriorsBeliefs before data: priors pull the fit, and ridge regression is a Gaussian prior in disguise.1–2 sa

Bayesian

1. Bayesian ReasoningUpdating beliefs with evidence: prior times likelihood, renormalized.1–2 sa
2. Conjugate Priors and Bayesian UpdatingBeta-Bernoulli and friends: priors that stay in the family after seeing data, making updating visible.1–2 sa
3. Bayesian Linear Regression and the Posterior PredictiveA distribution over lines instead of one line: uncertainty that grows away from the data.1–2 sa
4. Gaussian ProcessesPriors over functions defined by a kernel: Bayesian regression without a fixed parameter vector.1–2 sa

Trust

1. CalibrationDo 70% predictions happen 70% of the time? Reading reliability honestly.1–2 sa
2. Uncertainty: Aleatoric vs EpistemicNoise in the world vs ignorance in the model: two uncertainties, two remedies.1–2 sa
3. Conformal PredictionDistribution-free prediction sets with guaranteed coverage from a held-out calibration set.1–2 sa