Score: 0

uGMM-NN: Univariate Gaussian Mixture Model Neural Network

Published: September 9, 2025 | arXiv ID: 2509.07569v1

By: Zakeria Sharif Ali

Potential Business Impact:

Makes computers understand and guess better.

Business Areas:
Machine Learning Artificial Intelligence, Data and Analytics, Software

This paper introduces the Univariate Gaussian Mixture Model Neural Network (uGMM-NN), a novel neural architecture that embeds probabilistic reasoning directly into the computational units of deep networks. Unlike traditional neurons, which apply weighted sums followed by fixed nonlinearities, each uGMM-NN node parameterizes its activations as a univariate Gaussian mixture, with learnable means, variances, and mixing coefficients. This design enables richer representations by capturing multimodality and uncertainty at the level of individual neurons, while retaining the scalability of standard feedforward networks. We demonstrate that uGMM-NN can achieve competitive discriminative performance compared to conventional multilayer perceptrons, while additionally offering a probabilistic interpretation of activations. The proposed framework provides a foundation for integrating uncertainty-aware components into modern neural architectures, opening new directions for both discriminative and generative modeling.

Page Count
10 pages

Category
Computer Science:
Machine Learning (CS)