# Evolution under Length Constraints for CNN Architecture design

arXiv: https://arxiv.org/abs/2305.03416 · HTML: https://mlsanity.com/paper/2305.03416/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 52 references that are in the map.
- First posted on arXiv 5 May 2023.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [Network In Network](https://mlsanity.com/paper/1312.4400/) (2013)
- [Large-Scale Evolution of Image Classifiers](https://mlsanity.com/paper/1703.01041/) (2017)
- [Designing Neural Network Architectures using Reinforcement Learning](https://mlsanity.com/paper/1611.02167/) (2016)
- [Highway Networks](https://mlsanity.com/paper/1505.00387/) (2015)
- [Hierarchical Representations for Efficient Architecture Search](https://mlsanity.com/paper/1711.00436/) (2017)
- [Maxout Networks](https://mlsanity.com/paper/1302.4389/) (2013)
- [Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning](https://mlsanity.com/paper/1712.06567/) (2017)
- [Genetic CNN](https://mlsanity.com/paper/1703.01513/) (2017)
- [Neural Architecture Transfer](https://mlsanity.com/paper/2005.05859/) (2020)
- [A Genetic Programming Approach to Designing Convolutional Neural Network Architectures](https://mlsanity.com/paper/1704.00764/) (2017)
- [Evolving Deep Convolutional Neural Networks for Image Classification](https://mlsanity.com/paper/1710.10741/) (2017)
- [Automatically designing CNN architectures using genetic algorithm for image classification](https://mlsanity.com/paper/1808.03818/) (2018)
- [Hyperparameter Search in Machine Learning](https://mlsanity.com/paper/1502.02127/) (2015)
- [Flattened Convolutional Neural Networks for Feedforward Acceleration](https://mlsanity.com/paper/1412.5474/) (2014)
- [Practical Block-wise Neural Network Architecture Generation](https://mlsanity.com/paper/1708.05552/) (2017)

## Abstract (arXiv)

In recent years, the CNN architectures designed by evolution algorithms have proven to be competitive with handcrafted architectures designed by experts. However, these algorithms need a lot of computational power, which is beyond the capabilities of most researchers and engineers. To overcome this problem, we propose an evolution architecture under length constraints. It consists of two algorithms: a search length strategy to find an optimal space and a search architecture strategy based on genetic algorithm to find the best individual in the optimal space. Our algorithms reduce drastically resource cost and also keep good performance. On the Cifar-10 dataset, our framework presents outstanding performance with an error rate of 5.12% and only 4.6 GPU a day to converge to the optimal individual -22 GPU a day less than the lowest cost automatic evolutionary algorithm in the peer competition.