# Improving Neural Networks by Adopting Amplifying and Attenuating Neurons

## TL;DR

This paper introduces simple amplifying and attenuating neurons that can be integrated into neural networks to improve their performance without significant computational costs, supported by theoretical and experimental evidence.

## Contribution

It proposes novel neuron types that enhance neural network capabilities and demonstrates their effectiveness through theoretical analysis and numerical experiments.

## Key findings

- Amplifying neurons increase neural network order.
- Networks with these neurons achieve higher accuracy.
- Performance improvements are validated experimentally.

## Abstract

In the present study, an amplifying neuron and attenuating neuron, which can be easily implemented into neural networks without any significant additional computational effort, are proposed. The activated output value is squared for the amplifying neuron, while the value becomes its reciprocal for the attenuating one. Theoretically, the order of neural networks increases when the amplifying neuron is placed in the hidden layer. The performance assessments of neural networks were conducted to verify that the amplifying and attenuating neurons enhance the performance of neural networks. From the numerical experiments, it was revealed that the neural networks that contain the amplifying and attenuating neurons yield more accurate results, compared to those without them.