# Towards Physical Plausibility in Neuroevolution Systems

arXiv: https://arxiv.org/abs/2401.17733 · HTML: https://mlsanity.com/paper/2401.17733/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 20 references that are in the map.
- First posted on arXiv 31 Jan 2024.

## Builds on (most cited first, 7 of 7)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model](https://mlsanity.com/paper/2211.02001/) (2022)
- [Neural Architecture Search without Training](https://mlsanity.com/paper/2006.04647/) (2020)
- [The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink](https://mlsanity.com/paper/2204.05149/) (2022)
- [Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective](https://mlsanity.com/paper/2102.11535/) (2021)
- [Neuroevolution in Deep Neural Networks: Current Trends and Future Challenges](https://mlsanity.com/paper/2006.05415/) (2020)
- [DENSER: Deep Evolutionary Network Structured Representation](https://mlsanity.com/paper/1801.01563/) (2018)

## Built on by (most cited first, 3 of 3)

- [GreenMachine: Automatic Design of Zero-Cost Proxies for Energy-Efficient NAS](https://mlsanity.com/paper/2411.15290/) (2024)
- [GreenFactory: Ensembling Zero-Cost Proxies to Estimate Performance of Neural Networks](https://mlsanity.com/paper/2505.09344/) (2025)
- [EBA-AI: Ethics-Guided Bias-Aware AI for Efficient Underwater Image Enhancement and Coral Reef Monitoring](https://mlsanity.com/paper/2507.15036/) (2025)

## Abstract (arXiv)

The increasing usage of Artificial Intelligence (AI) models, especially Deep Neural Networks (DNNs), is increasing the power consumption during training and inference, posing environmental concerns and driving the need for more energy-efficient algorithms and hardware solutions. This work addresses the growing energy consumption problem in Machine Learning (ML), particularly during the inference phase. Even a slight reduction in power usage can lead to significant energy savings, benefiting users, companies, and the environment. Our approach focuses on maximizing the accuracy of Artificial Neural Network (ANN) models using a neuroevolutionary framework whilst minimizing their power consumption. To do so, power consumption is considered in the fitness function. We introduce a new mutation strategy that stochastically reintroduces modules of layers, with power-efficient modules having a higher chance of being chosen. We introduce a novel technique that allows training two separate models in a single training step whilst promoting one of them to be more power efficient than the other while maintaining similar accuracy. The results demonstrate a reduction in power consumption of ANN models by up to 29.2% without a significant decrease in predictive performance.