Code Monkey home page Code Monkey logo

sn_essay's Introduction

git地址:https://github.com/koukoulala/SN_essay.git 都是用DNN做的,迭代2000次 1.facebook数据集: 只看直接相邻的邻居数目的表:18列特征,18个类别,准确度0.98 只有第2种邻居结构的表:18列特征,18个类别,准确度0.90 只有第3种邻居结构的表:18列特征,18个类别,准确度0.89 3种邻居结构的表(第一列是全部邻居数目):54列特征,18个类别,准确度0.972 2.bcspwr数据集: 只看直接相邻的邻居数目的表:8列特征,8个类别,准确度0.8377 只有第2种邻居结构的表:8列特征,8个类别,准确度0.6396 只有第3种邻居结构的表:8列特征,8个类别,准确度0.2415 3种邻居结构的表(第一列是全部邻居数目):24列特征,8个类别,准确度0.8415 指定3种结构的影响度,直接测试准确率:都设置为1,准确度0.824;设置为(1,0,0)即只有直接相邻节点起作用的话,准确度0.821 使用cnn,把每个节点邻居结构看做是图,并且数目都10(为了防止梯度消失),测试集准确率0.8359,训练集最高0.86 使用cnn,把每个节点邻居结构看做是图,并且数目都10(为了防止梯度消失),第一列不是全部邻居,测试集准确率0.8613 改为无向图,第 13 次迭代时达到最大准确率为: 0.9921875,最大准确率时的权重值: 0.39824164 0.6255868 0.68378544 测试准确率为: 0.990188679245283,错误的总数目: 52 3.fpga数据集: 只看直接相邻的邻居数目的表:16列特征,16个类别,准确度0.9918 3种邻居结构的表(第一列是全部邻居数目):48列特征,16个类别,准确度0.9918

sn_essay's People

Contributors

koukoulala avatar

Watchers

James Cloos avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.