Symmetrical components: Difference between revisions

Revision as of 21:36, 6 January 2014

Template:Unreferenced stub Template:Orphan

Unique negative dimension (UND) is a complexity measure for the model of learning from positive examples. The unique negative dimension of a class $C$ of concepts is the size of the maximum subclass $D \subseteq C$ such that for every concept $c \in D$ , we have $\cap (D ∖ {c}) ∖ c$ is nonempty.

This concept was originally proposed by M. Gereb-Graus in "Complexity of learning from one-side examples", Technical Report TR-20-89, Harvard University Division of Engineering and Applied Science, 1989.

@@ Line 1: / Line 1: @@
-The title of the writer is Numbers but it's not the most masucline title out there. For a while she's been in South Dakota. To gather coins is what his family members and him appreciate. Hiring is her day job now but she's always needed her own business.<br><br>My blog :: at home std testing ([https://breakmedia.zendesk.com/entries/53044424-Cures-For-A-Candidiasis-Tips-To-Use-Now click this link now])
+{{Unreferenced stub|auto=yes|date=December 2009}}
+{{Orphan|date=December 2009}}
+'''Unique negative dimension''' (UND) is a complexity measure for the model of [[learning from positive examples]].
+The unique negative dimension of a class <math>C</math> of concepts is the size of the maximum subclass <math>D\subseteq C</math> such that for every concept <math>c\in D</math>, we have <math>\cap (D\setminus \{c\})\setminus c </math> is nonempty.
+This concept was originally proposed by M. Gereb-Graus in "Complexity of learning from one-side examples", Technical Report TR-20-89, Harvard University Division of Engineering and Applied Science, 1989.
+==See also==
+* [[Computational learning theory]]
+{{DEFAULTSORT:Unique Negative Dimension}}
+[[Category:Computational learning theory]]
+{{Compu-AI-stub}}

Symmetrical components: Difference between revisions

Revision as of 21:36, 6 January 2014

See also

Navigation menu

Search