arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2207.07720cs.LGmath.FA
收藏

局部逼近、实插值与机器学习

Local Approximations, Real Interpolation and Machine Learning

Johann Radon Institute for Computational and Applied Mathematics (RICAM), Austrian Academy of Sciences(奥地利科学院约翰·拉东计算与应用数学研究所);Linköping University(林雪平大学);RISE Research Institutes of Sweden AB(瑞典RISE研究院有限公司)

Eric Setterqvist, Natan Kruglyak, Robert Forchheimer

摘要:

我们提出了一种新的分类算法,是基于局部近似,并解释其与人工神经网络(ANN)和最近邻分类器的连接。我们说明它的数据集MNIST和EMNIST的手写数字图像。我们使用数据集MNIST来找到我们的算法的参数,并将其与这些参数一起应用于具有挑战性的EMNIST数据集。它表明,该算法错误分类的图像的EMNIST的0.42%,因此显着优于预测的人类和浅人工神经网络(ANN与几个隐藏层),都有超过1.3%的错误

英文摘要:

We suggest a novel classification algorithm that is based on local approximations and explain its connections with Artificial Neural Networks (ANNs) and Nearest Neighbour classifiers. We illustrate it on the datasets MNIST and EMNIST of images of handwritten digits. We use the dataset MNIST to find parameters of our algorithm and apply it with these parameters to the challenging EMNIST dataset. It is demonstrated that the algorithm misclassifies 0.42% of the images of EMNIST and therefore significantly outperforms predictions by humans and shallow artificial neural networks (ANNs with few hidden layers) that both have more than 1.3% of errors

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。

↑