基于ResNet框架的搜索空间，用验证损失辅助优化网络结构
A Neural Architecture Search Method using Auxiliary Evaluation Metric based on ResNet Architecture
- 以ResNet为基架构建搜索空间，优化卷积、池化、全连接和残差连接
- 在MNIST、Fashion-MNIST和CIFAR100上均获得可竞争的准确率
- 引入验证集损失作为辅助目标，提升搜索效率与结果稳定性
本文提出一种基于ResNet架构的神经网络架构搜索空间，搜索目标包括卷积层、池化层、全连接层的参数以及残差网络的连接方式。除了识别准确率外，本文还使用验证集上的损失值作为次要优化目标。实验结果表明，该搜索空间结合优化方法可在MNIST、Fashion-MNIST和CIFAR100数据集上找到具有竞争力的网络架构。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。