# Two Novel Performance Improvements for Evolving CNN Topologies

arXiv: https://arxiv.org/abs/2102.05451 · HTML: https://mlsanity.com/paper/2102.05451/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 16 references that are in the map.
- First posted on arXiv 10 Feb 2021.

## Builds on (most cited first, 4 of 4)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Large-Scale Evolution of Image Classifiers](https://mlsanity.com/paper/1703.01041/) (2017)
- [Genetic CNN](https://mlsanity.com/paper/1703.01513/) (2017)
- [Automatically designing CNN architectures using genetic algorithm for image classification](https://mlsanity.com/paper/1808.03818/) (2018)

## Abstract (arXiv)

Convolutional Neural Networks (CNNs) are the state-of-the-art algorithms for the processing of images. However the configuration and training of these networks is a complex task requiring deep domain knowledge, experience and much trial and error. Using genetic algorithms, competitive CNN topologies for image recognition can be produced for any specific purpose, however in previous work this has come at high computational cost. In this work two novel approaches are presented to the utilisation of these algorithms, effective in reducing complexity and training time by nearly 20%. This is accomplished via regularisation directly on training time, and the use of partial training to enable early ranking of individual architectures. Both approaches are validated on the benchmark CIFAR10 data set, and maintain accuracy.