machine Wiki Rss Feed

Updated Wiki: Home

SethJuarez — Mon, 04 Mar 2013 20:48:28 GMT

This project has been moved! Check out the new page.

Source code has also been moved to github.

Updated Wiki: Home

SethJuarez — Mon, 04 Mar 2013 20:47:18 GMT

This project has been moved! Check out the new page: http://numl.net

Source code has also been moved to github.

Updated Wiki: Home

SethJuarez — Mon, 04 Mar 2013 20:47:03 GMT

This project has been moved! Check out the new page: http://numl.net

Source code has also been moved to github.

Updated Wiki: Home

SethJuarez — Mon, 04 Mar 2013 20:46:01 GMT

This project has been moved! Check out the new page: http://numl.net

Updated Wiki: Home

SethJuarez — Mon, 04 Mar 2013 20:45:35 GMT

This project has been moved! Check out the new page: http://numl.net

Updated Wiki: Home

SethJuarez — Wed, 23 Feb 2011 23:27:51 GMT

Project Description

This library is designed to assist in the use of common Machine Learning Algorithms in conjunction with the .NET platform. It is designed to include the most popular supervised and unsupervised learning algorithms while minimizing the friction involved with creating the predictive models.

Supervised Learning

Supervised learning is an approach in machine learning where the system is provided with labeled examples of a problem and the computer creates a model to predict future unlabeled examples. These classifiers are further divided into the following sets:

Binary Classification – Predicting a Yes/No type value
Multi-Class Classification – Predicting a value from a finite set (i.e. {A, B, C, D } or {1, 2, 3, 4})
Regression – Predicting a continuous value (i.e. a number)

Currently the library contains:

The Perceptron Algorithm (Only supports binary classification for now)
Using this algorithm involves marking up a class with features (used to predict) and the target label (what to predict).

  1: public enum Grade
  2: {
  3:   A,
  4:   B,
  5:   C,
  6:   D,
  7:   F
  8: }
  9: 
 10: public class Student
 11: {
 12:   [Feature]
 13:   public string Name { get; set; }
 14: 
 15:   [Feature]
 16:   public Grade Grade { get; set; }
 17: 
 18:   [Feature]
 19:   public double GPA { get; set; }
 20: 
 21:   [Feature]
 22:   public int Age { get; set; }
 23: 
 24:   [Feature]
 25:   public bool Tall { get; set; }
 26: 
 27:   [Feature]
 28:   public int Friends { get; set; }
 29: 
 30:   [Label]
 31:   public bool Good { get; set; }
 32: }

Once a class is marked up in this fashion, the a classifier is generated from a list of objects instantiated from the data class. A new object can then be the target of prediction based on the model generated:

  1: var model = new PerceptronModel<Student>();
  2: var classifier = model.Generate(ListOfStudents);
  3: 
  4: classifier.Predict(NewStudentObject);

Decision Tree Classifier (Supports Binary and Multi-Class Classification)
The same labeling (attribute) technique is used to mark up a class definition.
Using the DT algorithm is similar to the above usage of the Perceptron algorithm:

  1: var model = new DecisionTreeModel<Student>(3, ImpurityType.Entropy);
  2: var predictor = model.Generate(ListOfStudents);
  3: 
  4: predictor.Predict(NewStudent);

This model has two additional parameters: Tree Height (which is set to 3 in this instance) and Impurity Measure to find information gain (this example uses Entropy: Gini and Max Error are also included).

Unsupervised Learning

Unsupervised learning is an approach which involves learning about the shape of unlabeled data. This library currently contains:

KMeans – Performs automatic grouping of data into K groups (specified a priori)
Labeling data is the same as for the supervised learning algorithms with the exception that these algorithms ignore the [Label] attribute:
```
  1: var kmeans = new KMeans<Student>();
  2: var grouping = kmeans.Generate(ListOfStudents, 2);
```
Here the KMeans algorithm is grouping the ListOfStudents into two groups returning an array corresponding to the appropriate group for each student (in this case group 0 or group 1)
Hierarchical Clustering – In progress!

Planning

Currently planning/hoping to do the following:

Boosting/Bagging
Hierarchical Clustering
Naïve Bayes Classifier
Collaborative filtering algorithms (suggest a product, friend etc.)
Latent Semantic Analysis (for better searching of text etc.)
Support Vector Machines (more powerful classifier)
Principal Component Analysis – Aids in dimensionality reduction which should allow/facilitate learning from images
*Maybe* – Common AI algorithms such as A*, Beam Search, Minimax etc.

Contact Me

You can email me at sethj AT devexpress.com or follow me on twitter: @sethjuarez.

Thanks to

for sponsoring and allowing me time to work on it!

Updated Wiki: Home

SethJuarez — Wed, 23 Feb 2011 23:20:07 GMT

Project Description

Supervised Learning

Binary Classification – Predicting a Yes/No type value
Multi-Class Classification – Predicting a value from a finite set (i.e. {A, B, C, D } or {1, 2, 3, 4})
Regression – Predicting a continuous value (i.e. a number)

Currently the library contains:

The Perceptron Algorithm (Only supports binary classification for now)
Using this algorithm involves marking up a class with features (used to predict) and the target label (what to predict).

  1: public enum Grade
  2: {
  3:   A,
  4:   B,
  5:   C,
  6:   D,
  7:   F
  8: }
  9: 
 10: public class Student
 11: {
 12:   [Feature]
 13:   public string Name { get; set; }
 14: 
 15:   [Feature]
 16:   public Grade Grade { get; set; }
 17: 
 18:   [Feature]
 19:   public double GPA { get; set; }
 20: 
 21:   [Feature]
 22:   public int Age { get; set; }
 23: 
 24:   [Feature]
 25:   public bool Tall { get; set; }
 26: 
 27:   [Feature]
 28:   public int Friends { get; set; }
 29: 
 30:   [Label]
 31:   public bool Good { get; set; }
 32: }

  1: var model = new PerceptronModel<Student>();
  2: var classifier = model.Generate(ListOfStudents);
  3: 
  4: classifier.Predict(NewStudentObject);

  1: var model = new DecisionTreeModel<Student>(3, ImpurityType.Entropy);
  2: var predictor = model.Generate(ListOfStudents);
  3: 
  4: predictor.Predict(NewStudent);

Unsupervised Learning

Unsupervised learning is an approach which involves learning about the shape of unlabeled data. This library currently contains:

KMeans – Performs automatic grouping of data into K groups (specified a priori)
Labeling data is the same as for the supervised learning algorithms with the exception that these algorithms ignore the [Label] attribute:
```
  1: var kmeans = new KMeans<Student>();
  2: var grouping = kmeans.Generate(ListOfStudents, 2);
```
Here the KMeans algorithm is grouping the ListOfStudents into two groups returning an array corresponding to the appropriate group for each student (in this case group 0 or group 1)
Hierarchical Clustering – In progress!

Planning

Currently planning/hoping to do the following:

Boosting/Bagging
Hierarchical Clustering
Naïve Bayes Classifier
Collaborative filtering algorithms (suggest a product, friend etc.)
Latent Semantic Analysis (for better searching of text etc.)
Support Vector Machines (more powerful classifier)
Principal Component Analysis – Aids in dimensionality reduction which should allow/facilitate learning from images
*Maybe* – Common AI algorithms such as A*, Beam Search, Minimax etc.

Contact Me

You can email me at sethj AT devexpress.com or follow me on twitter: @sethjuarez.

Updated Wiki: Home

SethJuarez — Wed, 23 Feb 2011 23:12:24 GMT

Project Description

Supervised Learning

Binary Classification – Predicting a Yes/No type value
Multi-Class Classification – Predicting a value from a finite set (i.e. {A, B, C, D } or {1, 2, 3, 4})
Regression – Predicting a continuous value (i.e. a number)

Currently the library contains:

The Perceptron Algorithm (Only supports binary classification for now)
Using this algorithm involves marking up a class with features (used to predict) and the target label (what to predict).

  1: public enum Grade
  2: {
  3:   A,
  4:   B,
  5:   C,
  6:   D,
  7:   F
  8: }
  9: 
 10: public class Student
 11: {
 12:   [Feature]
 13:   public string Name { get; set; }
 14: 
 15:   [Feature]
 16:   public Grade Grade { get; set; }
 17: 
 18:   [Feature]
 19:   public double GPA { get; set; }
 20: 
 21:   [Feature]
 22:   public int Age { get; set; }
 23: 
 24:   [Feature]
 25:   public bool Tall { get; set; }
 26: 
 27:   [Feature]
 28:   public int Friends { get; set; }
 29: 
 30:   [Label]
 31:   public bool Good { get; set; }
 32: }

  1: var model = new PerceptronModel<Student>();
  2: var classifier = model.Generate(ListOfStudents);
  3: 
  4: classifier.Predict(NewStudentObject);

  1: var model = new DecisionTreeModel<Student>(3, ImpurityType.Entropy);
  2: var predictor = model.Generate(ListOfStudents);
  3: 
  4: predictor.Predict(NewStudent);

Unsupervised Learning

Unsupervised learning is an approach which involves learning about the shape of unlabeled data. This library currently contains:

KMeans – Performs automatic grouping of data into K groups (specified a priori)
Labeling data is the same as for the supervised learning algorithms with the exception that these algorithms ignore the [Label] attribute:
```
  1: var kmeans = new KMeans<Student>();
  2: var grouping = kmeans.Generate(ListOfStudents, 2);
```
Here the KMeans algorithm is grouping the ListOfStudents into two groups returning an array corresponding to the appropriate group for each student (in this case group 0 or group 1)
Hierarchical Clustering – In progress!

Planning

Currently planning/hoping to do the following:

Boosting/Bagging
Hierarchical Clustering
Collaborative filtering algorithms (suggest a product, friend etc.)
Latent Semantic Analysis (for better searching of text etc.)
Support Vector Machines (more powerful classifier)
Principal Component Analysis – Aids in dimensionality reduction which should allow/facilitate learning from images
*Maybe* – Common AI algorithms such as A*, Beam Search, Minimax etc.

Contact Me

You can email me at sethj AT devexpress.com or follow me on twitter: @sethjuarez.

Updated Wiki: Home

SethJuarez — Wed, 23 Feb 2011 23:12:00 GMT

Project Description

Supervised Learning

Binary Classification – Predicting a Yes/No type value
Multi-Class Classification – Predicting a value from a finite set (i.e. {A, B, C, D } or {1, 2, 3, 4})
Regression – Predicting a continuous value (i.e. a number)

Currently the library contains:

The Perceptron Algorithm (Only supports binary classification for now)
Using this algorithm involves marking up a class with features (used to predict) and the target label (what to predict).

  1: public enum Grade
  2: {
  3:   A,
  4:   B,
  5:   C,
  6:   D,
  7:   F
  8: }
  9: 
 10: public class Student
 11: {
 12:   [Feature]
 13:   public string Name { get; set; }
 14: 
 15:   [Feature]
 16:   public Grade Grade { get; set; }
 17: 
 18:   [Feature]
 19:   public double GPA { get; set; }
 20: 
 21:   [Feature]
 22:   public int Age { get; set; }
 23: 
 24:   [Feature]
 25:   public bool Tall { get; set; }
 26: 
 27:   [Feature]
 28:   public int Friends { get; set; }
 29: 
 30:   [Label]
 31:   public bool Good { get; set; }
 32: }

  1: var model = new PerceptronModel<Student>();
  2: var classifier = model.Generate(ListOfStudents);
  3: 
  4: classifier.Predict(NewStudentObject);

Decision Tree Classifier (Supports Binary and Multi-Class Classification)
The same labeling (attribute) technique is used to mark up a class definition.
Using the DT algorithm is similar to the above usage of the Perceptron algorithm:

  1: var model = new DecisionTreeModel<Student>(3, ImpurityType.Entropy);
  2: var predictor = model.Generate(ListOfStudents);
  3: 
  4: predictor.Predict(NewStudent);

Unsupervised Learning

Unsupervised learning is an approach which involves learning about the shape of unlabeled data. This library currently contains:

KMeans – Performs automatic grouping of data into K groups (specified a priori)
Labeling data is the same as for the supervised learning algorithms with the exception that these algorithms ignore the [Label] attribute:
```
  1: var kmeans = new KMeans<Student>();
  2: var grouping = kmeans.Generate(ListOfStudents, 2);
```
Here the KMeans algorithm is grouping the ListOfStudents into two groups returning an array corresponding to the appropriate group for each student (in this case group 0 or group 1)
Hierarchical Clustering – In progress!

Planning

Currently planning/hoping to do the following:

Boosting/Bagging
Hierarchical Clustering
Collaborative filtering algorithms (suggest a product, friend etc.)
Latent Semantic Analysis (for better searching of text etc.)
Support Vector Machines (more powerful classifier)
Principal Component Analysis – Aids in dimensionality reduction which should allow/facilitate learning from images
*Maybe* – Common AI algorithms such as A*, Beam Search, Minimax etc.

Contact Me

You can email me at sethj AT devexpress.com or follow me on twitter: @sethjuarez.

Updated Wiki: Home

SethJuarez — Wed, 23 Feb 2011 23:09:32 GMT

Project Description

Supervised Learning

Binary Classification – Predicting a Yes/No type value
Multi-Class Classification – Predicting a value from a finite set (i.e. {A, B, C, D } or {1, 2, 3, 4})
Regression – Predicting a continuous value (i.e. a number)

Currently the library contains:

The Perceptron Algorithm (Only supports binary classification for now)
Using this algorithm involves marking up a class with features (used to predict) and the target label (what to predict).

  1: public class Student
  2: {
  3:   [Feature]
  4:   public double GradeToPercent()
  5:   {
  6:     double grade = 0;
  7:     switch (Grade)
  8:     {
  9:       case Grade.A:
 10:         grade = 90;
 11:         break;
 12:       case Grade.B:
 13:         grade = 80;
 14:         break;
 15:       case Grade.C:
 16:         grade = 70;
 17:         break;
 18:       case Grade.D:
 19:         grade = 60;
 20:         break;
 21:       case Grade.F:
 22:         grade = 50;
 23:         break;
 24:     }
 25:     return grade;
 26:   }
 27: 
 28:   public string Name { get; set; }
 29: 
 30:   public Grade Grade { get; set; }
 31: 
 32:   [Feature]
 33:   public double GPA { get; set; }
 34: 
 35:   [Feature]
 36:   public int Age { get; set; }
 37: 
 38:   [Feature]
 39:   public bool Tall { get; set; }
 40: 
 41:   [Feature]
 42:   public int Friends { get; set; }
 43: 
 44:   [Label]
 45:   public bool Good { get; set; }
 46: }

  1: var model = new PerceptronModel<Student>();
  2: var classifier = model.Generate(ListOfStudents);
  3: 
  4: classifier.Predict(NewStudentObject);

  1: var model = new DecisionTreeModel<Student>(3, ImpurityType.Entropy);
  2: var predictor = model.Generate(ListOfStudents);
  3: 
  4: predictor.Predict(NewStudent);

Unsupervised Learning

Unsupervised learning is an approach which involves learning about the shape of unlabeled data. This library currently contains:

KMeans – Performs automatic grouping of data into K groups (specified a priori)
Labeling data is the same as for the supervised learning algorithms with the exception that these algorithms ignore the [Label] attribute:
```
  1: var kmeans = new KMeans<Student>();
  2: var grouping = kmeans.Generate(ListOfStudents, 2);
```
Here the KMeans algorithm is grouping the ListOfStudents into two groups returning an array corresponding to the appropriate group for each student (in this case group 0 or group 1)
Hierarchical Clustering – In progress!

Planning

Currently planning/hoping to do the following:

Boosting/Bagging
Hierarchical Clustering
Collaborative filtering algorithms (suggest a product, friend etc.)
Latent Semantic Analysis (for better searching of text etc.)
Support Vector Machines (more powerful classifier)
Principal Component Analysis – Aids in dimensionality reduction which should allow/facilitate learning from images
*Maybe* – Common AI algorithms such as A*, Beam Search, Minimax etc.

Contact Me

You can email me at sethj AT devexpress.com or follow me on twitter: @sethjuarez.

Updated Wiki: Temporary Post Used For Theme Detection (4d8d0239-fe86-4953-bb1f-588dda696816 - 3bfe001a-32de-4114-a6b4-4005b770f6d7)

SethJuarez — Wed, 23 Feb 2011 22:36:48 GMT

This is a temporary post that was not deleted. Please delete this manually. (78b4a361-cea7-4a8e-b5e9-f5228b0941e7 - 3bfe001a-32de-4114-a6b4-4005b770f6d7)

Updated Wiki: Matrix.Dot

TimNelson — Tue, 08 Feb 2011 05:31:17 GMT

Matrix.Dot

This method calculates the “dot product” of a Matrix and Vector object.

The first overload takes a Matrix object as the first argument and a Vector object as a second argument. The dot product is then calculated by using each row in the matrix against the corresponding fields in the vector. For example:

var m = new Matrix(new double[,] 
    {{1,2},
     {3,4}});
var v = new Vector(new double[] {8,9});
var v2 = Matrix.Dot(m, v);
// v2 is now equal to:
// { (1*8)+(2*9), (3*8)+(4*9) } = { 26, 60 }

The second overload takes a Vector as the first argument and a Matrix as the second argument. The dot product is then calculated by using each column in the matrix against the corresponding fields in the vector. For example:

var m = new Matrix(new double[,] 
    {{1,2},
     {3,4}});
var v = new Vector(new double[] {8,9});
var v2 = Matrix.Dot(v, m);
// v2 is now equal to:
// { (1*8)+(3*9), (2*8)+(4*9) } = { 35, 52 }

Updated Wiki: Matrix Object

TimNelson — Tue, 08 Feb 2011 05:03:38 GMT

Static Methods

Cholesky
Dot
Eigs
FrobeniusNorm
Identity
LU
Norm
NormRand
Ones
QR
Rand
Round
Sum
SVD
Zeros

Methods

Cholesky
Eigs
GetCols
GetRows
GetVector
Indices
Norm
Remove
Round
Slice
Stack
Sum
SVD
ToVector
Trace
Transpose

Properties

Cols
Rows
T

Updated Wiki: Matrix.Dot

TimNelson — Tue, 08 Feb 2011 05:03:14 GMT

Matrix.Dot skeleton page

Updated Wiki: Matrix.Zeros

TimNelson — Tue, 08 Feb 2011 04:43:54 GMT

Matrix.Zeros

This static method returns a new Matrix object with all the values initialized to zero. The first overload takes a single integer n and returns an n by n matrix. The second overload takes two integers (n,d) and returns a Matrix object with n rows and d columns.

Updated Wiki: Matrix.Ones

TimNelson — Tue, 08 Feb 2011 04:43:40 GMT

Matrix.Ones

This static method returns a new Matrix object with all the values initialized to one. The first overload takes a single integer n and returns an n by n matrix. The second overload takes two integers (n,d) and returns a Matrix object with n rows and d columns.

Updated Wiki: Matrix.Identity

TimNelson — Tue, 08 Feb 2011 04:43:02 GMT

Matrix.Identity

This static method returns a new identity matrix of the requested size. The first overload takes a single integer n and returns an n by n matrix. The second overload takes two integers (n,d) and returns a Matrix object with n rows and d columns.

An identity matrix is an {m, n} matrix with all values where m != n are zero and all values where m == n are one. For example:

var identity = Matrix.Identity(3);
// identity is
// {{1, 0, 0},
//  {0, 1, 0},
//  {0, 0, 1}}
//
// notice that all values are zero except identity[0,0], identity[1,1] and identity[2,2].

Updated Wiki: Matrix Object

TimNelson — Tue, 08 Feb 2011 04:12:00 GMT

Static Methods

Cholesky
Dot
Eigs
FrobeniusNorm
Identity
LU
Norm
NormRand
Ones
QR
Rand
Round
Sum
SVD
Zeros

Methods

Cholesky
Eigs
GetCols
GetRows
GetVector
Indices
Norm
Remove
Round
Slice
Stack
Sum
SVD
ToVector
Trace
Transpose

Properties

Cols
Rows
T

Updated Wiki: Matrix.Identity

TimNelson — Tue, 08 Feb 2011 04:10:28 GMT

Matrix.Identity skeleton page.

Updated Wiki: Matrix.Ones

TimNelson — Tue, 08 Feb 2011 04:08:50 GMT