In statistics, KDE/KDC is a type of non-parametric regression to estimate the density function of a random variable(s)

KDE/KDC - How it Works & Compared to Histogram

where:

Bandwidth (ℎ)	Kernel Function (𝑘)

Kernel Density Estimate (KDE) with different bandwidths of a random sample of 100 points from a standard normal distribution: grey: true density (standard normal) red: KDE with ℎ=0.05 black: KDE with ℎ=0.337 green: KDE with ℎ=2	see Kernel Functions (Similarity Functions)

Kernel Density Estimate (KDE) with different bandwidths of a random sample of 100 points from a standard normal distribution:

KDE/KDC - Types

Histogram	KDE with a Dirac Delta kernel with bandwidth = 0
k-Nearest Neighbors	KDE with a uniform kernel with variable bandwidth to encompass 𝑘 nearest neighbors
Gaussian Process Regression (GPR) - Kriging	KDE with Gaussian kernel (can use other kernel types)
Kernel Regression	a non-parametric regression technique in statistics to estimate the conditional expectation of a random variable