source: branches/2839_HiveProjectManagement/HeuristicLab.Algorithms.DataAnalysis/3.4/KernelRidgeRegression/KernelFunctions/GaussianKernel.cs @ 16057

Last change on this file since 16057 was 16057, checked in by jkarder, 14 months ago

#2839:

File size: 2.4 KB
Line 
1#region License Information
2/* HeuristicLab
3 * Copyright (C) 2002-2018 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
4 *
5 * This file is part of HeuristicLab.
6 *
7 * HeuristicLab is free software: you can redistribute it and/or modify
8 * it under the terms of the GNU General Public License as published by
9 * the Free Software Foundation, either version 3 of the License, or
10 * (at your option) any later version.
11 *
12 * HeuristicLab is distributed in the hope that it will be useful,
13 * but WITHOUT ANY WARRANTY; without even the implied warranty of
14 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
15 * GNU General Public License for more details.
16 *
17 * You should have received a copy of the GNU General Public License
18 * along with HeuristicLab. If not, see <http://www.gnu.org/licenses/>.
19 */
20#endregion
21
22using System;
23
24using HeuristicLab.Common;
25using HeuristicLab.Core;
26
27using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
28
29namespace HeuristicLab.Algorithms.DataAnalysis {
30  [StorableClass]
31  [Item("GaussianKernel", "A kernel function that uses Gaussian function exp(-n²/beta²). As described in http://crsouza.com/2010/03/17/kernel-functions-for-machine-learning-applications/")]
32  public class GaussianKernel : KernelBase {
33    [StorableConstructor]
34    protected GaussianKernel(bool deserializing) : base(deserializing) { }
35
36    protected GaussianKernel(GaussianKernel original, Cloner cloner) : base(original, cloner) { }
37
38    public GaussianKernel() {
39    }
40
41    public override IDeepCloneable Clone(Cloner cloner) {
42      return new GaussianKernel(this, cloner);
43    }
44
45    protected override double Get(double norm) {
46      if (Beta == null) throw new InvalidOperationException("Can not calculate kernel distance while Beta is null");
47      var beta = Beta.Value;
48      if (Math.Abs(beta) < double.Epsilon) return double.NaN;
49      var d = norm / beta;
50      return Math.Exp(-d * d);
51    }
52
53    //2 * n²/b²* 1/b * exp(-n²/b²)
54    protected override double GetGradient(double norm) {
55      if (Beta == null) throw new InvalidOperationException("Can not calculate kernel distance gradient while Beta is null");
56      var beta = Beta.Value;
57      if (Math.Abs(beta) < double.Epsilon) return double.NaN;
58      var d = norm / beta;
59      return 2 * d * d / beta * Math.Exp(-d * d);
60    }
61  }
62}
Note: See TracBrowser for help on using the repository browser.