arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.08935math.NAcs.NA
收藏

自适应双层ReLU神经网络:I.最佳最小二乘逼近

Adaptive Two-Layer ReLU Neural Network: I. Best Least-squares Approximation

Min Liu, Zhiqiang Cai, Jingshuang Chen

摘要:

在本文中,我们介绍了自适应神经元增强(ANE)方法的最佳最小二乘逼近使用两层ReLU神经网络(NN)。对于给定的函数f(x),ANE方法生成双层ReLU NN和数值积分网格,使得近似精度在规定的公差内。ANE方法提供了一个获得良好初始化的自然过程,这对于训练非线性最优化问题至关重要。ANE方法的数值结果的两个变量的功能表现出相交的界面奇点或尖锐的内层。

英文摘要:

In this paper, we introduce adaptive neuron enhancement (ANE) method for the best least-squares approximation using two-layer ReLU neural networks (NNs). For a given function f(x), the ANE method generates a two-layer ReLU NN and a numerical integration mesh such that the approximation accuracy is within the prescribed tolerance. The ANE method provides a natural process for obtaining a good initialization which is crucial for training nonlinear optimization problems. Numerical results of the ANE method are presented for functions of two variables exhibiting either intersecting interface singularities or sharp interior layers.

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。

↑