m |
m |
||
Line 1: | Line 1: | ||
− | One way to represent classifiers. Given classes | + | One way to represent classifiers. |
+ | Given classes <math>w_1, w_2, \ldots, w_k</math> and feature vector x, which is in n-dimensional space, the discriminant functions <math>g_1(x), g_2(x), \ldots, g_k(x)</math> where <math>g_\#(x)</math> maps n-dimensional space to real numbers, are used to make decisions. Decisions are defined as <math>w_\#</math> if <math>g_\#(x) >= g_j(x)</math> for all j. | ||
Discriminant functions are used to define [[Decision Surfaces_Old Kiwi]]. | Discriminant functions are used to define [[Decision Surfaces_Old Kiwi]]. |
Latest revision as of 09:53, 10 April 2008
One way to represent classifiers. Given classes $ w_1, w_2, \ldots, w_k $ and feature vector x, which is in n-dimensional space, the discriminant functions $ g_1(x), g_2(x), \ldots, g_k(x) $ where $ g_\#(x) $ maps n-dimensional space to real numbers, are used to make decisions. Decisions are defined as $ w_\# $ if $ g_\#(x) >= g_j(x) $ for all j.
Discriminant functions are used to define Decision Surfaces_Old Kiwi.