arXivDaily arXiv每日学术速递 周一至周五更新
arXiv cs/0310050cs.NE
收藏

具有扩散非线性权函数的前馈神经网络

Feedforward Neural Networks with Diffused Nonlinear Weight Functions

Artur Rataj

摘要:

在本文中,前馈神经网络提出了具有非线性权函数的基础上查找表,这是特别平滑的正则化称为扩散。这种类型的网络的想法是基于这样的假设,即每个权重函数的自适应参数的数量越多,可能会减少解决给定问题所需的权重函数的总数。然后,如果通过单个这样的权重函数的传播的计算复杂性将保持较低,则引入的神经网络可能相对较快。进行了大量的测试,表明所提出的神经网络可能确实在某些情况下比经典的神经网络和其他一些学习机更好地执行。

英文摘要:

In this paper, feedforward neural networks are presented that have nonlinear weight functions based on look--up tables, that are specially smoothed in a regularization called the diffusion. The idea of such a type of networks is based on the hypothesis that the greater number of adaptive parameters per a weight function might reduce the total number of the weight functions needed to solve a given problem. Then, if the computational complexity of a propagation through a single such a weight function would be kept low, then the introduced neural networks might possibly be relatively fast. A number of tests is performed, showing that the presented neural networks may indeed perform better in some cases than the classic neural networks and a number of other learning machines.

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。

↑