SOM classifier - Revision history

Akivela: /* SOM classification example */

2012-02-16T19:30:09Z

‎SOM classification example

Akivela: /* Additional notes */

2011-11-07T10:22:44Z

‎Additional notes

Akivela at 07:58, 12 November 2010

2010-11-12T07:58:32Z

Akivela: /* SOM classification example */

2009-10-17T08:55:49Z

‎SOM classification example

Akivela: /* SOM classification example */

2009-09-11T14:00:10Z

‎SOM classification example

Akivela: /* SOM classification example */

2009-09-11T13:37:41Z

‎SOM classification example

Akivela: /* SOM classification example */

2009-09-11T13:36:30Z

‎SOM classification example

Akivela: /* SOM classification example */

2009-09-11T13:35:28Z

‎SOM classification example

Akivela: /* SOM classification example */

2009-09-11T13:25:42Z

‎SOM classification example

Akivela: /* Additional notes */

2008-10-12T07:52:02Z

‎Additional notes

← Older revision		Revision as of 19:30, 16 February 2012
Line 87:		Line 87:


−	Below is screenshot of associations created in previous screenshot. Note the association type and roles. As the semantic interpretation of topics in same node is not ~~evident~~, a general association type '''SOM-Group-1220093644251''' is used. The number sequence is there just to distinguish different groups. User can change the base name and subject identifiers of group's association type later in Wandora, if necessary. Each group is an instance of '''SOM-Group''' topic.	+	Below is screenshot of associations created in previous screenshot. Note the association type and roles. As the semantic interpretation of topics in same node is not clear, a general association type '''SOM-Group-1220093644251''' is used. The number sequence is there just to distinguish different groups. User can change the base name and subject identifiers of group's association type later in Wandora, if necessary. Each group is an instance of '''SOM-Group''' topic.

@@ Line 49: / Line 49: @@
 * If your training set is very large (>1000 grouping topics and/or training vector dimension is >1000), the matrix training may take a while.
 * Different runs with same source data may result different SOMs due initial random vectors in neurons matrix.
-* My intuition says you get best results if training vectors are not orthogonal.
+* My intuition says you get best results if training vectors are '''not''' orthogonal.
 * SOM classifier assumes source associations are binary.
 * For more information about Self Organizing Maps read

@@ Line 36: / Line 36: @@
   loop
     select training vector
-    for selected training vector
+    for the selected training vector
       select best matching matrix node
-      for best matching matrix node
+      for the best matching matrix node
-        adjust the best matching vector in node and it's neighbours with training vector
+        adjust the best matching vector in node and it's neighbors with the training vector
 When training ends, the matrix contains adapted neurons. Due to the training method, neurons resemble training vectors and nearby neurons are generally more similar than distant neurons. Multi dimensional input space i.e. training vectors can now be visualized with two dimensional plane i.e the matrix.

← Older revision		Revision as of 08:55, 17 October 2009
Line 57:		Line 57:
	== SOM classification example ==		== SOM classification example ==

−	Lets say we have a large topic map containing artworks and keywords. Each artwork has been tagged with relevant keywords i.e topic map contains ~~association~~ between artworks and keywords. In our example each keyword tags multiple artworks and each artwork has multiple tags. We select all the artwork-keyword associations as shown below and start '''SOM classifier''' in context of selection. We select '''Artworks''' as the grouping role.	+	Lets say we have a large topic map containing artworks and keywords. Each artwork has been tagged with relevant keywords i.e topic map contains associations between artworks and keywords. In our example each keyword tags multiple artworks and each artwork has multiple tags. We select all the artwork-keyword associations as shown below and start '''SOM classifier''' in context of selection. We select '''Artworks''' as the grouping role.

← Older revision		Revision as of 14:00, 11 September 2009
Line 74:		Line 74:


−	Now Wandora user can browse the visualization and perform topic map operations using the collected data. For example Wandora user may create associations that group topics in selected nodes. In general topics placed into same node should somehow resemble each other. Below is a screenshot of SOM visualization where user has selected three nodes and is about to create such grouping associations.	+	Now Wandora user can browse the visualization and perform topic map operations using the collected data. Bottom left slider is used to zoom in the matrix. Clicking a cell in the matrix selects cells. To select multiple cells hold SHIFT or CTRL key down. Right clicking the cell reveals context menu with options:
		+
		+	* Selecting and deselecting cells
		+	* Copying cell data to system clipboard. This may be useful if you want further analyze outcome of the SOM learning process.
		+	* Copy matrix as an image.
		+	* Create associations between topics labeling training vectors. You can create associations with '''Group''' and '''Permutate''' options. '''Group''' options create a specific group topic and associates each training vector label topic with the group topic (see image below). '''Permutate''' option is used create associations between training vector label topics.
		+
		+	For example Wandora user may create associations that group topics in selected nodes. In general topics placed into same node should somehow resemble each other. Below is a screenshot of SOM visualization where user has selected three nodes and is about to create such grouping associations.

← Older revision		Revision as of 13:37, 11 September 2009
Line 63:		Line 63:


−	Wandora builds up training vectors and neuron matrix, and trains the matrix with vectors. Finally training sequence ends and Wandora opens up a visualization of the matrix. Then Wandora places all artwork topics to best matching nodes of the matrix. Below is an example of such visualization. White edge squares represent neuron matrix cells. Empty squares have no matching training vectors that is artworks in our example. Cells with tiny text have matching training vectors. Some cells have even multiple matching training vectors. Each line in the cell represents one match. Black horizontal pixel line at the bottom of the cell is a counter for matches. One pixel in the line represents one match.	+	Wandora builds up training vectors and neuron matrix, and trains the matrix with vectors. Finally training sequence ends and Wandora opens up a visualization of the matrix. Then Wandora places all artwork topics to best matching nodes of the matrix. Below is an example of such visualization. White edge squares represent neuron matrix cells. Empty squares have no matching training vectors that is artworks in our example. Cells with tiny text have matching training vectors. Some cells have even multiple matching training vectors. Each text line in the cell represents one match. Black horizontal pixel line at the bottom of the cell is a counter for matches. One pixel in the line represents one match.

	User can now draw conclusions using the visualization		User can now draw conclusions using the visualization

← Older revision		Revision as of 13:36, 11 September 2009
Line 63:		Line 63:


−	Wandora builds up training vectors and neuron matrix, and trains the matrix with vectors. Finally training sequence ends and Wandora opens up a visualization of the matrix. Then Wandora places all artwork topics to best matching nodes of the matrix. Below is an example of such visualization. White edge squares represent neuron matrix cells. Empty squares have no matching training vectors that is artworks in our example. Cells with tiny text have matching training vectors. Some cells have even multiple matching training vectors. Each line in the cell represents one match. Black ~~one~~ pixel line at the bottom of the cell is a counter for matches. One pixel in line represents one match.	+	Wandora builds up training vectors and neuron matrix, and trains the matrix with vectors. Finally training sequence ends and Wandora opens up a visualization of the matrix. Then Wandora places all artwork topics to best matching nodes of the matrix. Below is an example of such visualization. White edge squares represent neuron matrix cells. Empty squares have no matching training vectors that is artworks in our example. Cells with tiny text have matching training vectors. Some cells have even multiple matching training vectors. Each line in the cell represents one match. Black horizontal pixel line at the bottom of the cell is a counter for matches. One pixel in the line represents one match.

	User can now draw conclusions using the visualization		User can now draw conclusions using the visualization

@@ Line 65: / Line 65: @@
 Wandora builds up training vectors and neuron matrix, and trains the matrix with vectors. Finally training sequence ends and Wandora opens up a visualization of the matrix. Then Wandora places all artwork topics to best matching nodes of the matrix. Below is an example of such visualization. White edge squares represent neuron matrix cells. Empty squares have no matching training vectors that is artworks in our example. Cells with tiny text have matching training vectors. Some cells have even multiple matching training vectors. Each line in the cell represents one match. Black one pixel line at the bottom of the cell is a counter for matches. One pixel in line represents one match.
-User can now draw conclusions about the visualization
+User can now draw conclusions using the visualization
 * Training vectors (=artworks) locating same cell ought to be very similar, even identical.
 * Training vectors (=artworks) locating near cells ought to be similar.

← Older revision		Revision as of 13:25, 11 September 2009
Line 63:		Line 63:


−	Wandora builds up training vectors and neuron matrix, and trains the matrix with vectors. Finally training sequence ends and Wandora opens up a visualization of the matrix. Then Wandora places all artwork topics to best matching nodes of the matrix. Below is an example of such visualization.	+	Wandora builds up training vectors and neuron matrix, and trains the matrix with vectors. Finally training sequence ends and Wandora opens up a visualization of the matrix. Then Wandora places all artwork topics to best matching nodes of the matrix. Below is an example of such visualization. White edge squares represent neuron matrix cells. Empty squares have no matching training vectors that is artworks in our example. Cells with tiny text have matching training vectors. Some cells have even multiple matching training vectors. Each line in the cell represents one match. Black one pixel line at the bottom of the cell is a counter for matches. One pixel in line represents one match.
		+
		+	User can now draw conclusions about the visualization
		+	* Training vectors (=artworks) locating same cell ought to be very similar, even identical.
		+	* Training vectors (=artworks) locating near cells ought to be similar.
		+	* Training vectors (=artworks) locating far away cells ought to be different.