用户名  找回密码
 To register

QQ登录

只需一步,快速开始

扫一扫,访问微社区

Titlebook: Artificial Intelligence and Soft Computing; 12th International C Leszek Rutkowski,Marcin Korytkowski,Jacek M. Zurad Conference proceedings

[复制链接]
楼主: Objective
发表于 2025-3-26 22:21:05 | 显示全部楼层
发表于 2025-3-27 03:23:49 | 显示全部楼层
发表于 2025-3-27 05:32:38 | 显示全部楼层
https://doi.org/10.1007/978-3-642-66599-8implementations were measured and compared. In the ESN case, speed-ups were observed at reservoir sizes greater than 1,024. The first significant speed-ups of 6 and and 5 were observed at a reservoir size of 2,048 in double and single precision respectively. In the case of Tikhonov Regularisation, no significant speed-ups were observed.
发表于 2025-3-27 09:30:43 | 显示全部楼层
发表于 2025-3-27 14:19:41 | 显示全部楼层
https://doi.org/10.1007/978-3-662-21539-5 terms. The proposed approach is based on a random sieve that aims at selecting only necessary RBF’s by a hierarchy of a large number of random mixing of candidate RBF’s and testing their significance. The results of simulations are also reported.
发表于 2025-3-27 18:02:32 | 显示全部楼层
A New Method of Centers Location in Gaussian RBF Interpolation Networkse Latin hypercube designs and a space-filling curve based space-filling designs as starting points for the optimization procedure. We restrict our attention to 1-D and 2-D interpolation problems. Finally, we provide results of several numerical experiments. We compare the performance of this new method with the method of [6].
发表于 2025-3-27 22:41:20 | 显示全部楼层
发表于 2025-3-28 05:18:03 | 显示全部楼层
Testing the Generalization of Feedforward Neural Networks with Median Neuron Input Function The MIF networks were designed to be fault tolerant but we expect them to have also improved generalization ability. Results of first experimental simulations are presented and described in this article. Potentially improved performance of the MIF networks is demonstrated.
发表于 2025-3-28 06:17:08 | 显示全部楼层
发表于 2025-3-28 13:06:19 | 显示全部楼层
Conference proceedings 2013ft Computing, ICAISC 2013, held in Zakopane, Poland in June 2013. The 112 revised full papers presented together with one invited paper were carefully reviewed and selected from 274 submissions. The 57 papers included in the first volume are organized in the following topical sections: neural networ
 关于派博传思  派博传思旗下网站  友情链接
派博传思介绍 公司地理位置 论文服务流程 影响因子官网 SITEMAP 大讲堂 北京大学 Oxford Uni. Harvard Uni.
发展历史沿革 期刊点评 投稿经验总结 SCIENCEGARD IMPACTFACTOR 派博系数 清华大学 Yale Uni. Stanford Uni.
|Archiver|手机版|小黑屋| 派博传思国际 ( 京公网安备110108008328) GMT+8, 2025-6-7 21:59
Copyright © 2001-2015 派博传思   京公网安备110108008328 版权所有 All rights reserved
快速回复 返回顶部 返回列表