Gaussian Process Regression From First Principles

By Medium - 2021-03-15

Description

Gaussian Process Regression (GPR) is a remarkably powerful class of machine learning algorithms that, in contrast to many of today’s state-of-the-art machine learning models, relies on few parameters…

Summary

  • Gaussian Process Regression is a remarkably powerful class of machine learning algorithms.
  • Estimates of the mean of f(x) are produced as a linear combination of observed target values y.
  • The weighting coefficients used to produce these mean estimates are independent of the target values, placing Gaussian Process Regression models into the class of linear smoothers [1].
  • Photo by Siora Photography on Unsplash Covariance functions are a crucial component of GPR models, sincethese functions weight the contributions of training points to predicted test targets according to the kernel distance between observed training points X and test points X∗.
  • Recall from the previous section that one way to conceptualize GPR prediction is as a linear smoothing mechanism: An example of time series mean and variance prediction using Gaussian Process Regression.

 

Topics

  1. Machine_Learning (0.5)
  2. Backend (0.19)
  3. NLP (0.16)

Similar Articles

Facebook’s Prophet + Deep Learning = NeuralProphet

By Medium - 2020-12-10

While learning about time series forecasting, sooner or later you will encounter the vastly popular Prophet model, developed by Facebook. It gained lots of popularity due to the fact that it provides…