Optimal Classification

Author(s):  
Ulisses Braga-Neto
Author(s):  
Charles A. Doan ◽  
Ronaldo Vigo

Abstract. Several empirical investigations have explored whether observers prefer to sort sets of multidimensional stimuli into groups by employing one-dimensional or family-resemblance strategies. Although one-dimensional sorting strategies have been the prevalent finding for these unsupervised classification paradigms, several researchers have provided evidence that the choice of strategy may depend on the particular demands of the task. To account for this disparity, we propose that observers extract relational patterns from stimulus sets that facilitate the development of optimal classification strategies for relegating category membership. We conducted a novel constrained categorization experiment to empirically test this hypothesis by instructing participants to either add or remove objects from presented categorical stimuli. We employed generalized representational information theory (GRIT; Vigo, 2011b , 2013a , 2014 ) and its associated formal models to predict and explain how human beings chose to modify these categorical stimuli. Additionally, we compared model performance to predictions made by a leading prototypicality measure in the literature.


2014 ◽  
Vol 687-691 ◽  
pp. 1462-1465
Author(s):  
Zhi Liang Zhang

This paper mainly discusses the optimal solution for hyper-sphere integral classification process of big data. The paper proposes an optimal calculation method for the target problem. Through statistics and analysis of big data, we get the constraint condition, and calculate a maximum value of data characteristic. Then, by the dual programming of Quadratic Programming, we obtain the optimal classification function for hyper-sphere integral classification process of big data. The experiment results show that the proposed algorithm can significantly improve the accuracy of the classification hyper-sphere integral for big data.


1999 ◽  
Vol 13 (01) ◽  
pp. 33-41 ◽  
Author(s):  
M. ANDRECUT

An optimal statistical perceptron algorithm is derived using the Bayes classification theory. The described algorithm is able to construct an optimal classification hyperplane for separable and nonseparable classes. The described algorithm can be easily improved by imposing a simple fuzzyfication scheme of the training sets.


Author(s):  
Ibraim Didmanidze ◽  
Givi Tsitskishvili

In scientific work it is shown, that our goal is to choose the desired option from variety of alternatives (in our case different options of loading-unloading operations on the vessel) or to take decision which is the best (optimal). Classification in this case is the grounds, as taking the choice is based on choosing certain class, which can be assigned to an alternative. Stratification and rating gives us wide option to make reasonable selection, or to take a kind of decision which will be optimal for the certain moment and occasion. These methods can be used with equal strength at all stages of the processes taking place in the area of current decision making management. This refers to the object of our study of course – solution of selecting optimal option to optimize loading-unloading operation on the vessel. It goes without saying that variety of alternatives doesn’t have any structure, thus abundance of each element was never structured randomly retrieved or no consideration has been proposed, and they are not a priority and in any order. Coming out of this it’s impossible to mention which alternative is better and which is less desirable. In order to solve the task of selecting a set of alternatives successfully, it is necessary, to make structure of the given abundance of alternatives in any form.


Sign in / Sign up

Export Citation Format

Share Document