Non-Parametric Regression

Energy Based Process

Introduced by Yang et al. in Energy-Based Processes for Exchangeable Data

Energy Based Processes extend energy based models to exchangeable data while allowing neural network parameterizations of the energy function. They extend the previously separate stochastic process and latent variable model perspectives in a common framework. The result is a generalization of Gaussian processes and Student-t processes that exploits EBMs for greater flexibility.

Source: Energy-Based Processes for Exchangeable Data

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Denoising 1 50.00%
Point Cloud Generation 1 50.00%

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories