Voisin, J. and Devijver, P. A. 1987. An application of the Multiedit-Condensing technique to the reference selection problem in a print recognition system. Pattern Recognition 5:465--474. 14 Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Prototype and Feature Selection by Sampling and Random.. - David Skalak Department (1994) (84 citations) (Correct)
.... Reduced Nearest Neighbor algorithm [Gates, 1972] IB2 [Aha, 1990] storing typical instances [Zhang, 1992] storing only training instances that have been correctly classified by other training instances [Wilson, 1972] exploiting domain knowledge [Kurtzberg, 1987] and combining these techniques [Voisin and Devijver, 1987]. Other systems deal with reference selection by storing averages or abstractions of instances. For discussions of these approaches, see [Aha, 1990] Aha s research [1990] has shown that classification accuracy can be improved by limiting the number of prototypes and by weighting features. See ....
Voisin, J. and Devijver, P. A. 1987. An application of the Multiedit-Condensing technique to the reference selection problem in a print recognition system. Pattern Recognition 5:465--474. 14
Transformation Invariance in Pattern Recognition -.. - Simard, Le Cun.. (1998) (42 citations) (Correct)
....to train the tangentvectors Finally,many optimizations which are commonly used in distance based algorithms can be used as successfully with Tangent Distance to speed up computation. The multi resolution approach have already been tried successfully [25] Other methods like multi edit condensing [1, 30] and K d tree [4] are also possible. The main advantage of Tangent Distance is that it is a modification of a standard distance measure to allow it to incorporate a priori knowledge that is specific to your problem. Any algorithms based on a common distance measure (as it is often the case in ....
Jean Voisin and Pierre Devijver. An application of the multiedit-condensing technique to the reference selection problem in a print recognition system. Pattern Recogntion, 20 No 5:465--474, 1987.
Forgetting Exceptions is Harmful in Language Learning - Daelemans, van den Bosch.. (1999) (24 citations) (Correct)
.... Several functions for computing class prediction strength have been proposed, e.g. as a criterion for removing instances in memory based (k nn) learning algorithms, such as ib3 (Aha, Kibler, and Albert, 1991) cf. earlier work on edited k nn (Hart, 1968; Wilson, 1972; Devijver and Kittler, 1980; Voisin and Devijver, 1987)) or for weighting instances in the Each algorithm (Salzberg, 1990) We use the class prediction strength function as proposed by Salzberg (1990) This is the ratio of the number of times the instance type is a nearest neighbor of another instance with the same class and the number of times that ....
Voisin, J. and P. A. Devijver. 1987. An application of the Multiedit-Condensing technique to the reference selection problem in a print recognition system. Pattern Recognition, 5:465--474.
Do Not Forget: Full Memory in Memory-Based Learning of.. - van den Bosch, Daelemans (1998) (3 citations) (Correct)
.... the training set (including itself) Several functions for computing classprediction strength have been proposed, e.g. as a criterion for removing instances in memory based (k nn) learning algorithms, such as ib3 (Aha, Kibler, and Albert, 1991) cf. earlier work on edited k nn (Wilson, 1972; Voisin and Devijver, 1987)) or for weighting instances in the Each algorithm (Salzberg, 1990; Cost and Salzberg, 1993) We chose to implement the straightforward class prediction strength function as proposed in (Salzberg, 1990) in two steps. First, we count (a) the number of times that the instance type is the nearest ....
Voisin, J. and P. A. Devijver. 1987. An application of the Multiedit-Condensing technique to the reference selection problem in a print recognition system. Pattern Recognition, 5:465--474.
Prototype Selection for Composite Nearest Neighbor Classifiers - Skalak (1995) (10 citations) (Correct)
.... instances ( Hart, 1968; Gates, 1972; Aha, 1990 ] storing typical instances [ Zhang, 1992 ] storing only training instances that have been correctly classified by other training instances [ Wilson, 1972 ] exploiting domain knowledge [ Kurtzberg, 1987 ] and combining these techniques [ Voisin and Devijver, 1987 ] Other systems deal with reference selection by storing averages or abstractions of instances [ Chang, 1974; de la Maza, 1991 ] In the next two sections, we survey important representatives of editing algorithms. 18 2.3.1 Pattern Recognition Editing Algorithms In this section, we review ....
Voisin, J. and Devijver, P. A. 1987. An application of the Multiedit-Condensing technique to the reference selection problem in a print recognition system. Pattern Recognition 5:465--474.
The Omnipresence of Case-Based Reasoning in Science and Application - Aha (1998) (5 citations) (Correct)
.... This line of research has been more empirically inclined, with a focus on thresholding (Sebestyen, 1962) iterative deletion (Gates, 1973) and domain specific feature selection (Kurtzberg, 1987) Naturally, a combination of these two strategies has also been investigated in detail (e.g. Voisin Devijer, 1987). Dasarathy s (1991) collection contains several classic papers related to this research. Interest in the AI community on case deletion is strong. For example, the 1995 IJCAI best paper award was given to a paper on this topic (Smyth Keane, 1995) Thus, it is probable that several of the ....
Voisin, J., & Devijver, P. A. (1987). An application of the Multiedit-Condensing technique to the reference selection problem in a print recognition system. Pattern Recognition, 5, 465--474.
Prototype Selection for Composite Nearest Neighbor Classifiers - Skalak (1997) (10 citations) (Correct)
.... instances [Hart, 1968; Gates, 1972; Aha, 1990] storing typical instances [Zhang, 1992] storing only training instances that have been correctly classified by other training 67 instances [Wilson, 1972] exploiting domain knowledge [Kurtzberg, 1987] and combining these techniques [Voisin and Devijver, 1987] . Stochastic search algorithms for prototype selection have been applied by Skalak [1994] and Cameron Jones [1995] Still other systems deal with prototype selection by storing averages or abstractions of instances [Chang, 1974; de la Maza, 1991] Filtering Algorithms. Table 2.1 collects the ....
Voisin, J. and Devijver, P. A. 1987. An application of the Multiedit-Condensing technique to the reference selection problem in a print recognition system. Pattern Recognition 5:465--474.
Prototype and Feature Selection by Sampling and Random Mutation.. - Skalak (1994) (84 citations) (Correct)
No context found.
Voisin, J. and Devijver, P. A. 1987. An application of the Multiedit-Condensing technique to the reference selection problem in a print recognition system. Pattern Recognition 5:465--474.
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