Z. Dar'oczy, "Generalized information functions," Information and Control, vol. 16, pp. 36--51, 1970. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Quantum Information Theory - Barnum, III (1998) (Correct)
....derive the Shannon information I(p 1 ; p i ; p n ) j X i p i log p i (2.4) as the only measure (up to a constant factor) satisfying these axioms. This is an oversimplification capturing the spirit of a slightly more technical argument, with slightly different axioms, due to Dar oczy [8]. Viewed in this light, the obvious generalization of information to quantum mechanics is that it should quantify the degree to which we know which state in Hilbert space a system is in. The Shannon information of our probability distribution over the states in the system s Hilbert space would be ....
Z. Dar'oczy, "Generalized information functions," Information and Control, vol. 16, pp. 36--51, 1970.
Evaluation Measures for Learning Probabilistic and.. - Borgelt, Kruse (1997) (Correct)
....I sgr = I gain HAB = I gain Gamma P i;j P (a i ; b j ) log 2 P (a i ; b j ) Because of its symmetry it is also applicable for undirected edges. The measures discussed above are all based on Shannon entropy, which can be seen as a special case (for fi 1) of generalized entropy [5]: H fi (p 1 ; p r ) r X i=1 p i 2 fi Gamma1 2 fi Gamma1 Gamma 1 (1 Gamma p fi Gamma1 i ) Setting fi = 2 yields the quadratic entropy H 2 (p 1 ; p r ) r X i=1 2p i (1 Gamma p i ) 2 Gamma 2 r X i=1 p 2 i : Using it in a similar way as Shannon ....
Z. Dar'oczy. Generalized Information Functions. Information and Control 16:36--51, 1970
Some Experimental Results on Learning Probabilistic and.. - Borgelt, Kruse (1997) (Correct)
....edge selections as the previous one. Nevertheless it is useful to consider both measures, since their effects can differ, if weighting is used (see section 5) The measures discussed above are all based on Shannon entropy, which can be seen as a special case (for fi 1) of generalized entropy [5]: H fi (p 1 ; p r ) r X i=1 p i 2 fi Gamma1 2 fi Gamma1 Gamma 1 (1 Gamma p fi Gamma1 i ) Setting fi = 2 yields the quadratic entropy H 2 (p 1 ; p r ) r X i=1 2p i (1 Gamma p i ) 2 Gamma 2 r X i=1 p 2 i : Using it in a similar way as Shannon ....
Z. Dar'oczy. Generalized Information Functions. Information and Control 16:36--51, 1970
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC