# Transmission Neural Networks: From Virus Spread Models to Neural Networks

arXiv: https://arxiv.org/abs/2208.03616 · HTML: https://mlsanity.com/paper/2208.03616/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 50 references that are in the map.
- First posted on arXiv 7 Aug 2022.

## Builds on (most cited first, 10 of 10)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)](https://mlsanity.com/paper/1511.07289/) (2015)
- [Universal Approximation with Deep Narrow Networks](https://mlsanity.com/paper/1905.08539/) (2019)
- [A survey on modern trainable activation functions](https://mlsanity.com/paper/2005.00817/) (2020)
- [The Modern Mathematics of Deep Learning](https://mlsanity.com/paper/2105.04026/) (2021)
- [Epidemic processes in complex networks](https://mlsanity.com/paper/1408.2701/) (2014)
- [Influence maximization in complex networks through optimal percolation](https://mlsanity.com/paper/1506.08326/) (2015)
- [Analysis and Control of Epidemics: A survey of spreading processes on complex networks](https://mlsanity.com/paper/1505.00768/) (2015)
- [Containing epidemic outbreaks by message-passing techniques](https://mlsanity.com/paper/1309.2805/) (2013)
- [Percolation on sparse networks](https://mlsanity.com/paper/1405.0483/) (2014)

## Built on by (most cited first, 1 of 1)

- [Transmission Neural Networks: Inhibitory and Excitatory Connections](https://mlsanity.com/paper/2604.04246/) (2026)

## Abstract (arXiv)

This work connects models for virus spread on networks with their equivalent neural network representations. Based on this connection, we propose a new neural network architecture, called Transmission Neural Networks (TransNNs) where activation functions are primarily associated with links and are allowed to have different activation levels. Furthermore, this connection leads to the discovery and the derivation of three new activation functions with tunable or trainable parameters. Moreover, we prove that TransNNs with a single hidden layer and a fixed non-zero bias term are universal function approximators. Finally, we present new fundamental derivations of continuous time epidemic network models based on TransNNs.