公开1万张LeNet-5模型数据集，助力超网络研究
An open dataset of neural networks for hypernetwork research
- 构建1万个不同LeNet-5模型，每类1000个用于二分类
- 用机器学习可识别模型差异，准确率达72.0%
- 适合研究超网络、模型生成与神经架构分析者
尽管人工智能潜力巨大，但能够生成其他神经网络权重的超网络研究仍不充分，主要因缺乏可用资源。本文提出一个专为超网络研究设计的数据集，包含10⁴个训练好的LeNet-5模型，用于二值图像分类，分为10类，每类对应ImageNette V2中的一个类别，共1,000个模型。该数据集由超过10⁴核心的计算集群生成。基础分类实验表明，使用监督学习算法可识别模型差异，准确率达72.0%。数据集及生成代码已开源，旨在推动超网络研究发展。
原文摘要 · Abstract (English)
Despite the transformative potential of AI, the concept of neural networks that can produce other neural networks by generating model weights (hypernetworks) has been largely understudied. One of the possible reasons is the lack of available research resources that can be used for the purpose of hypernetwork research. Here we describe a dataset of neural networks, designed for the purpose of hypernetworks research. The dataset includes $10^4$ LeNet-5 neural networks trained for binary image classification separated into 10 classes, such that each class contains 1,000 different neural networks that can identify a certain ImageNette V2 class from all other classes. A computing cluster of over $10^4$ cores was used to generate the dataset. Basic classification results show that the neural networks can be classified with accuracy of 72.0%, indicating that the differences between the neural networks can be identified by supervised machine learning algorithms. The ultimate purpose of the dataset is to enable hypernetworks research. The dataset and the code that generates it are open and accessible to the public.
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。