matlab调整代码大小写-deepMKL:跨度深度多核学习

上传者: 38670391 | 上传时间: 2022-04-07 15:22:35 | 文件大小: 37KB | 文件类型: ZIP
matlab调整代码大小写描述 这是一种算法,它通过与跨度边界交替优化来调整深层多内核网络。 这是尝试将深度学习扩展到较小的样本量。 该算法在Strobl EV(Visweswaran S.深度多核学习)中进行了详细描述。 ICMLA,2013年。 代码 首先,请安装MATLAB版本的LIBSVM()。 然后,下载此处上传的整个软件包(包括实用程序功能)。 主要方法 deepMKL_train.m-训练网络。 每层都有一个RBF,poly2,poly3和线性核。 如果跨度增加,则学习率可能会太高。 默认值在许多情况下都适用,但是可能需要进行一些调整。 deepMKL_test.m-测试网络

文件下载

资源详情

[{"title":"( 32 个子文件 37KB ) matlab调整代码大小写-deepMKL:跨度深度多核学习","children":[{"title":"deepMKL-master","children":[{"title":"README.md <span style='color:#111;'> 807B </span>","children":null,"spread":false},{"title":"Utilities","children":[{"title":"grad3Layer.m <span style='color:#111;'> 1.38KB </span>","children":null,"spread":false},{"title":"rbf.m <span style='color:#111;'> 118B </span>","children":null,"spread":false},{"title":"computeKernels.m <span style='color:#111;'> 593B </span>","children":null,"spread":false},{"title":"TwoLayerDeriv.m <span style='color:#111;'> 861B </span>","children":null,"spread":false},{"title":"grad2Layer.m <span style='color:#111;'> 936B </span>","children":null,"spread":false},{"title":"grad1Layer.m <span style='color:#111;'> 453B </span>","children":null,"spread":false},{"title":"normalizeKernel.m <span style='color:#111;'> 71B </span>","children":null,"spread":false},{"title":"DetermineSig.m <span style='color:#111;'> 170B </span>","children":null,"spread":false},{"title":"rbf2.m <span style='color:#111;'> 63B </span>","children":null,"spread":false},{"title":"PairWiseDistance.m <span style='color:#111;'> 134B </span>","children":null,"spread":false},{"title":"ThreeLayerDeriv.m <span style='color:#111;'> 1.13KB </span>","children":null,"spread":false},{"title":"SpanBoundDeriv.m <span style='color:#111;'> 1.03KB </span>","children":null,"spread":false},{"title":"SetDefaultValue.m <span style='color:#111;'> 225B </span>","children":null,"spread":false}],"spread":false},{"title":"Data","children":[{"title":"Australian_Dataset","children":[{"title":"Australian_TrainData.mat <span style='color:#111;'> 5.49KB </span>","children":null,"spread":false},{"title":"Australian_TestLabels.mat <span style='color:#111;'> 287B </span>","children":null,"spread":false},{"title":"Australian_TestData.mat <span style='color:#111;'> 5.44KB </span>","children":null,"spread":false},{"title":"Australian_TrainLabels.mat <span style='color:#111;'> 287B </span>","children":null,"spread":false}],"spread":true},{"title":"loadGermanDataset.m <span style='color:#111;'> 348B </span>","children":null,"spread":false},{"title":"loadAustralianDataset.m <span style='color:#111;'> 384B </span>","children":null,"spread":false},{"title":"German_Dataset","children":[{"title":"German_TestData.mat <span style='color:#111;'> 5.04KB </span>","children":null,"spread":false},{"title":"German_TrainLabels.mat <span style='color:#111;'> 304B </span>","children":null,"spread":false},{"title":"German_TestLabels.mat <span style='color:#111;'> 309B </span>","children":null,"spread":false},{"title":"German_TrainData.mat <span style='color:#111;'> 5.07KB </span>","children":null,"spread":false}],"spread":true},{"title":"loadTicTacToeDataset.m <span style='color:#111;'> 357B </span>","children":null,"spread":false},{"title":"TicTacToe_Dataset","children":[{"title":"TicTacToe_TrainLabels.mat <span style='color:#111;'> 332B </span>","children":null,"spread":false},{"title":"TicTacToe_TestData.mat <span style='color:#111;'> 1.31KB </span>","children":null,"spread":false},{"title":"TicTacToe_TestLabels.mat <span style='color:#111;'> 326B </span>","children":null,"spread":false},{"title":"TicTacToe_TrainData.mat <span style='color:#111;'> 1.32KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"MainMethods","children":[{"title":"deepMKL_train.m <span style='color:#111;'> 1.84KB </span>","children":null,"spread":false},{"title":"deepMKL_test.m <span style='color:#111;'> 683B </span>","children":null,"spread":false}],"spread":true},{"title":"demo.m <span style='color:#111;'> 1.25KB </span>","children":null,"spread":false}],"spread":true}],"spread":true}]

评论信息

免责申明

【只为小站】的资源来自网友分享,仅供学习研究,请务必在下载后24小时内给予删除,不得用于其他任何用途,否则后果自负。基于互联网的特殊性,【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查;无论 【只为小站】 经营者是否已进行审查,用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场,基于网友分享,根据中国法律《信息网络传播权保护条例》第二十二条之规定,若资源存在侵权或相关问题请联系本站客服人员,zhiweidada#qq.com,请把#换成@,本站将给予最大的支持与配合,做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明