14 citations · 16 across the 10 of their papers we have counts for
7 papers · 1 filter
On Maximum Entropy Linear Feature Inversion
Paul M Baggenstoss
We revisit the classical problem of inverting dimension-reducing linear mappings using the maximum entropy (MaxEnt) criterion. In the literature, solutions are problem-dependent, i…
Projected Belief Networks With Discriminative Alignment for Acoustic Event Classification: Rivaling State of the Art CNNs
Paul M. Baggenstoss, Kevin Wilkinghoff, Felix Govaers +1
The projected belief network (PBN) is a generative stochastic network with tractable likelihood function based on a feed-forward neural network (FFNN). The generative function oper…
A Comparison of PDF Projection with Normalizing Flows and SurVAE
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. However, NF is restricted to…
Improved Auto-Encoding using Deterministic Projected Belief Networks
Paul M Baggenstoss
In this paper, we exploit the unique properties of a deterministic projected belief network (D-PBN) to take full advantage of trainable compound activation functions (TCAs). A D-PB…
Using the Projected Belief Network at High Dimensions
Paul M Baggenstoss
The projected belief network (PBN) is a layered generative network (LGN) with tractable likelihood function, and is based on a feed-forward neural network (FFNN). There are two ver…
Trainable Compound Activation Functions for Machine Learning
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 func…
Maximum Entropy Auto-Encoding
Paul M Baggenstoss
In this paper, it is shown that an auto-encoder using optimal reconstruction significantly outperforms a conventional auto-encoder. Optimal reconstruction uses the conditional mean…