# A Neural Architecture Search Method using Auxiliary Evaluation Metric based on ResNet Architecture

arXiv: https://arxiv.org/abs/2505.01313 · HTML: https://mlsanity.com/paper/2505.01313/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 22 references that are in the map.
- First posted on arXiv 2 May 2025.

## Builds on (most cited first, 12 of 12)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Single Path One-Shot Neural Architecture Search with Uniform Sampling](https://mlsanity.com/paper/1904.00420/) (2019)
- [Evolving Deep Convolutional Neural Networks for Image Classification](https://mlsanity.com/paper/1710.10741/) (2017)
- [BackEISNN: A Deep Spiking Neural Network with Adaptive Self-Feedback and Balanced Excitatory-Inhibitory Neurons](https://mlsanity.com/paper/2105.13004/) (2021)
- [PRE-NAS: Predictor-assisted Evolutionary Neural Architecture Search](https://mlsanity.com/paper/2204.12726/) (2022)
- [BenchENAS: A Benchmarking Platform for Evolutionary Neural Architecture Search](https://mlsanity.com/paper/2108.03856/) (2021)
- [Evolution of Activation Functions for Deep Learning-Based Image Classification](https://mlsanity.com/paper/2206.12089/) (2022)

## Abstract (arXiv)

This paper proposes a neural architecture search space using ResNet as a framework, with search objectives including parameters for convolution, pooling, fully connected layers, and connectivity of the residual network. In addition to recognition accuracy, this paper uses the loss value on the validation set as a secondary objective for optimization. The experimental results demonstrate that the search space of this paper together with the optimisation approach can find competitive network architectures on the MNIST, Fashion-MNIST and CIFAR100 datasets.