arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.09015cs.LG
收藏

基于统计模型的神经网络评价

Statistical model-based evaluation of neural networks

KTH Royal Institute of Technology(KTH皇家理工学院)

Sandipan Das, Prakash B. Gohain, Alireza M. Javid, Yonina C. Eldar, Saikat Chatterjee

摘要:

使用基于统计模型的数据生成,我们开发了一个实验装置的评估神经网络(NN)。该设置有助于对一组NN与最小均方误差(MMSE)性能界限进行基准测试。这允许我们测试训练数据大小、数据维度、数据几何形状、噪声以及训练和测试条件之间的不匹配的影响。在建议的设置中,我们使用高斯混合分布来生成用于训练和测试一组竞争NN的数据。我们的实验表明,了解数据的类型和统计条件对于正确应用和设计神经网络的重要性

英文摘要:

Using a statistical model-based data generation, we develop an experimental setup for the evaluation of neural networks (NNs). The setup helps to benchmark a set of NNs vis-a-vis minimum-mean-square-error (MMSE) performance bounds. This allows us to test the effects of training data size, data dimension, data geometry, noise, and mismatch between training and testing conditions. In the proposed setup, we use a Gaussian mixture distribution to generate data for training and testing a set of competing NNs. Our experiments show the importance of understanding the type and statistical conditions of data for appropriate application and design of NNs

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑