人工神经网络源码(Artificial neural network source code).docVIP

人工神经网络源码(Artificial neural network source code).doc

  1. 1、原创力文档(book118)网站文档一经付费(服务费),不意味着购买了该文档的版权,仅供个人/单位学习、研究之用,不得用于商业用途,未经授权,严禁复制、发行、汇编、翻译或者网络传播等,侵权必究。。
  2. 2、本站所有内容均由合作方或网友上传,本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺!文档内容仅供研究参考,付费前请自行鉴别。如您付费,意味着您自己接受本站规则且自行承担风险,本站不退款、不进行额外附加服务;查看《如何避免下载的几个坑》。如果您已付费下载过本站文档,您可以点击 这里二次下载
  3. 3、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等,请点击“版权申诉”(推荐),也可以打举报电话:400-050-0827(电话支持时间:9:00-18:30)。
  4. 4、该文档为VIP文档,如果想要下载,成为VIP会员后,下载免费。
  5. 5、成为VIP后,下载本文档将扣除1次下载权益。下载后,不支持退款、换文档。如有疑问请联系我们
  6. 6、成为VIP后,您将拥有八大权益,权益包括:VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
  7. 7、VIP文档为合作方或网友上传,每下载1次, 网站将根据用户上传文档的质量评分、类型等,对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档
查看更多
人工神经网络源码(Artificial neural network source code)

人工神经网络源码(Artificial neural network source code) Chapter 7 the first procedure Glyunshu. M The function main () CLC % CLS Clear all; % clear memory to speed up the operation Close all; % close all current figure images SamNum = 20. The number of input samples is 20 TestSamNum = 20. The number of test samples is also 20 ForcastSamNum = 2; The number of predicted samples is 2 HiddenUnitNum = 8; The number of middle layer hidden nodes is 8, 1 more than the toolbox program InDim = 3; The network input dimension is 3 OutDim = 2; The network output dimension is 2 % raw data Number of people (unit: 10,000) SQRS = [20.55, 22.44, 25.37, 29.45, 34.06, 34.06, 36.42, 39.13 39.99... ; % motor vehicle number (unit: 10,000 units) SQJDCS = [0.6 0.75 0.75 0.85 0.9 1.35 1.35 1.85 2.15 2.25 2.35 2.5 2.6... 2.7 2.85 2.95 3.1]; Road area (unit: square kilometer) SQGLMJ = [0.09 0.11.0.11.0.14 0.23 0.23 0.32 0.32 0.32.0.36 0.36 0.38 0.49... ; Road passenger traffic volume (unit: 10,000) Glkyl = [5126 6217 7730 9145 10460 11387 12353 15750 18304 19836 21024 1949020433... (22598 25107 33442 36836 40548 42927 43462); Percent road cargo traffic (unit: 10,000 tons) Glhyl = [1237, 1379, 1385, 1399, 1663, 1714, 1834, 322, 8936, 11203, 10524 11115... 2. P = [SQRS SQJDCS; SQGLMJ]; % input data matrix T = [glkyl glhyl]; The % target data matrix [SamIn, minp, maxp, tn, mint, maxt] = premnmx (p, t); The original sample pairs (input and output) initialization Rand ( state , sum (100 * clock)) generates random Numbers based on the system clock seed NoiseVar = 0.01; The noise intensity is 0.01 (the purpose of adding noise is to prevent overfitting of the network) Whose = NoiseVar * randn (2, SamNum); % generating noise SamOut = tn + Noise; % will add noise to the output sample TestSamIn = SamIn; The sample is the same as the test sample because the sample size is small TestSamOut = SamOut; The sample is the same as the test sample MaxEpochs = 50000; The maximum training number is 50000 Lr = 0.035; The le

您可能关注的文档

文档评论(0)

jgx3536 + 关注
实名认证
文档贡献者

该用户很懒,什么也没介绍

版权声明书
用户编号:6111134150000003

1亿VIP精品文档

相关文档