[ Skip to the content ]

Institute of Formal and Applied Linguistics Wiki

• ÚFAL Wiki Home
• ÚFAL Home
• Sitemap
• RSS
• ÚFAL calendar
• Recent changes
• Login
• Hledat:

[ Back to the navigation ]

Differences

This shows you the differences between two versions of the page.

View differences: Side by SideInline Go

Link to this comparison view

Both sides previous revision Previous revision 2012/12/16 23:44 machacek 2012/12/16 23:40 machacek 2012/12/16 23:02 machacek 2012/12/16 22:40 machacek 2012/12/16 21:59 machacek 2012/12/16 21:34 machacek 2012/12/16 21:32 machacek 2012/12/16 21:07 machacek 2012/12/16 17:43 machacek 2012/12/16 17:43 machacek 2012/12/16 17:37 machacek 2012/12/16 17:36 machacek 2012/12/16 17:08 machacek 2012/12/16 16:46 machacek 2012/12/16 16:25 machacek 2012/12/16 16:25 machacek 2012/12/16 16:04 machacek 2012/12/16 15:56 machacek 2012/12/16 15:39 machacek 2012/12/16 15:25 machacek 2012/12/16 15:23 machacek vytvořeno Go		2012/12/16 23:44 machacek 2012/12/16 23:40 machacek 2012/12/16 23:02 machacek 2012/12/16 22:40 machacek 2012/12/16 21:59 machacek 2012/12/16 21:34 machacek 2012/12/16 21:32 machacek 2012/12/16 21:07 machacek 2012/12/16 17:43 machacek 2012/12/16 17:43 machacek 2012/12/16 17:37 machacek 2012/12/16 17:36 machacek 2012/12/16 17:08 machacek 2012/12/16 16:46 machacek 2012/12/16 16:25 machacek 2012/12/16 16:25 machacek 2012/12/16 16:04 machacek 2012/12/16 15:56 machacek 2012/12/16 15:39 machacek 2012/12/16 15:25 machacek 2012/12/16 15:23 machacek vytvořeno Go Next revision Both sides next revision
courses:rg:2012:distributed-perceptron [2012/12/16 16:25] machacek		courses:rg:2012:distributed-perceptron [2012/12/16 16:46] machacek
Line 45:		Line 45:
	w = [?, ?]		w = [?, ?]
-	Answer:	+	**Answer 1:**
-	Acording to English [[http://en.wikipedia.org/wiki/Perceptron#Multiclass_perceptron|Wikipedia]]: This multiclass formulation reduces to the original perceptron when **x** is a real-valued vector, y is chosen from {0,1}, and f(x,y) = y * **x**.	+	f(**x**,y) = (y == 0) ? (**x**, 0,0,...,0) : (0,0,...,0,**x**)
		+
		+	**Answer 2:**
		+
		+	Acording to English [[http://en.wikipedia.org/wiki/Perceptron#Multiclass_perceptron|Wikipedia]]: This multiclass formulation reduces to the original perceptron when **x** is a real-valued vector, y is chosen from {0,1}, and f(**x**,y) = y * **x**.
	However, I would say, that this holds only for activation treshold = 0. Therefore, this formula cannot be used to compute example from Question 1.		However, I would say, that this holds only for activation treshold = 0. Therefore, this formula cannot be used to compute example from Question 1.
		+
	==== Question 3 ====		==== Question 3 ====

---

[ Back to the navigation ] [ Back to the content ]