From the course: Probability Foundations for Data Science
Join today to access over 24,900 courses taught by industry experts.
Maximum a posteriori estimation (MAP)
From the course: Probability Foundations for Data Science
Maximum a posteriori estimation (MAP)
- [Instructor] Let's move on to the next estimation technique. Maximum A Posteriori Estimation, also known as MAP, is a method used in Bayesian probability to estimate an unknown parameter by maximizing the posterior distribution. This parameter equals the mode of the posterior distribution. It combines the prior information about the parameter with the likelihood of the observed data to provide a more robust estimation. Maximum A Posteriori Estimation is closely related to Maximum Likelihood Estimation. The Maximum A Posteriori Estimation method employs an augmented optimization objective that incorporates a prior distribution to quantify additional information available through prior information about the parameter being estimated. Maximum A Posteriori Estimation is therefore a regularization of Maximum Likelihood Estimation. This is due to the prior information being incorporated. Related to your earlier work with Bayes' Theorem, the Posterior Distribution combines the prior…
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.