線性核分類

Imports Accord.ControlsImports Accord.IOImports Accord.MathImports Accord.Statistics.Distributions.UnivariateImports Accord.MachineLearning.VectorMachines.LearningImports Accord.StatisticsImports SystemPublic Class Form1'SVM線性分類'使用Accord.IO里的的excel讀取類Dim table As DataTable = New ExcelReader("E:\pro\books\AI_.net\src\AI_learn\learnai-1\data\examples.xls").GetWorksheet("Classification - Yin Yang")Private Sub Button1_Click(sender As Object, e As EventArgs) Handles Button1.ClickNaiveBayes()End SubPrivate Sub NaiveBayes()'讀取樣本' 轉換datatable為輸入輸出數組Dim sample As Double()() = table.ToJagged(Of Double)("X", "Y")Dim outs As Integer() = table.Columns("G").ToArray(Of Integer)()Dim trainer As New LinearCoordinateDescent()Dim svm = trainer.Learn(sample, outs)Dim predictResult As Boolean() = svm.Decide(sample)Dim zeroOneAnswers As Integer() = predictResult.ToZeroOne()ScatterplotBox.Show("實際結果", sample, outs)ScatterplotBox.Show("SVM預測結果", sample, zeroOneAnswers).Hold()End SubEnd Class

效果如下

非線性高斯核分類

Imports Accord.Controls Imports Accord.IO Imports Accord.Math Imports Accord.Statistics.Distributions.Univariate Imports Accord.MachineLearning.VectorMachines.Learning Imports Accord.Statistics Imports Accord.Statistics.Kernels Imports SystemPublic Class Form1'SVM非線性核'使用Accord.IO里的的excel讀取類Dim table As DataTable = New ExcelReader("E:\pro\books\AI_.net\src\AI_learn\data\examples.xls").GetWorksheet("Classification - Yin Yang")Private Sub Button1_Click(sender As Object, e As EventArgs) Handles Button1.ClickNaiveBayes()End SubPrivate Sub NaiveBayes()'讀取樣本' 轉換datatable為輸入輸出數組Dim sample As Double()() = table.ToJagged(Of Double)("X", "Y")Dim outs As Integer() = table.Columns("G").ToArray(Of Integer)()Dim trainer As New SequentialMinimalOptimization(Of Gaussian)trainer.UseComplexityHeuristic = Truetrainer.UseKernelEstimation = TrueDim svm = trainer.Learn(sample, outs)Dim predictResult As Boolean() = svm.Decide(sample)Dim zeroOneAnswers As Integer() = predictResult.ToZeroOne()ScatterplotBox.Show("實際結果", sample, outs)ScatterplotBox.Show("SVM預測結果", sample, zeroOneAnswers).Hold()End Sub End Class

總結

以上是生活随笔為你收集整理的.net随笔-vb.net Accord.Net机器学习之SVM分类的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。