no code implementations • 11 May 2016 • Bo Tang, Steven Kay, Haibo He, Paul M. Baggenstoss
In this letter, we present a novel exponentially embedded families (EEF) based classification method, in which the probability density function (PDF) on raw data is estimated from the PDF on features.
no code implementations • 21 Jun 2016 • Bo Tang, Paul M. Baggenstoss, Haibo He
The recognition diversity indicates that a hybrid combination of the proposed generative classifier and the discriminative classifier could further improve the classification performance.
no code implementations • 18 Feb 2020 • Paul M. Baggenstoss
This posterior has a well-defined mean, the conditional mean estimator, that is calculated using a type of neural network with theoretically-derived activation functions similar to sigmoid, softplus, and relu.
no code implementations • 14 Aug 2020 • Paul M. Baggenstoss
The projected belief network (PBN) is a layered generative network with tractable likelihood function, and is based on a feed-forward neural network (FF-NN).
no code implementations • 25 Apr 2022 • Paul M. Baggenstoss
Activation functions (AF) are necessary components of neural networks that allow approximation of functions, but AFs in current use are usually simple monotonically increasing functions.
no code implementations • 24 Nov 2023 • Paul M. Baggenstoss, Felix Govaers
Normalizing flows (NF) recently gained attention as a way to construct generative networks with exact likelihood calculation out of composable layers.
no code implementations • 20 Jan 2024 • Paul M. Baggenstoss, Kevin Wilkinghoff, Felix Govaers, Frank Kurth
The PBN is two networks in one, a FFNN that operates in the forward direction, and a generative network that operates in the backward direction.