# Single neuron-based neural networks are as efficient as dense deep neural networks in binary and multi-class recognition problems

## TL;DR

This study shows that sparse, single neuron-based neural networks can match the performance of dense networks in recognition tasks, challenging the assumption that complexity is necessary for high accuracy.

## Contribution

It demonstrates that single neuron networks are capable of high-dimensional recognition, offering a simpler alternative to dense neural networks.

## Key findings

- Sparse networks perform as well as dense networks in recognition tasks.
- Single neuron networks excel in binary classification.
- Combined single neuron networks achieve competitive multi-class recognition results.

## Abstract

Recent advances in neuroscience have revealed many principles about neural processing. In particular, many biological systems were found to reconfigure/recruit single neurons to generate multiple kinds of decisions. Such findings have the potential to advance our understanding of the design and optimization process of artificial neural networks. Previous work demonstrated that dense neural networks are needed to shape complex decision surfaces required for AI-level recognition tasks. We investigate the ability to model high dimensional recognition problems using single or several neurons networks that are relatively easier to train. By employing three datasets, we test the use of a population of single neuron networks in performing multi-class recognition tasks. Surprisingly, we find that sparse networks can be as efficient as dense networks in both binary and multi-class tasks. Moreover, single neuron networks demonstrate superior performance in binary classification scheme and competing results when combined for multi-class recognition.