Upper-bound estimates for classifiers based on a dissimilarity function

Rusyn, B.; Tayanov, V.; Lutsyka, O.
July 2012
Cybernetics & Systems Analysis;Jul2012, Vol. 48 Issue 4, p592
Academic Journal
Approaches to calculating upper-bound estimates of recognition probability are proposed that can be used for a more general class of models. One of estimates determines the stability of object coverage by classification algorithms on the basis of distribution of distances between objects, and another estimate is underlain by leave-one-out cross-validation. This considerably simplifies and facilitates the construction of estimates.


Related Articles

  • THE MATHEMATICS OF POKER: BASIC EQUITY CALCULATIONS AND ESTIMATES. Farag, Mark // Mathematics & Computer Education;Winter2010, Vol. 44 Issue 1, p22 

    The article discusses basic equity calculations and estimates used when playing poker. It highlights the importance of employing mathematical considerations in some poker situations. It offers information on the rules of poker. The author believes that the other discussion will be of interest...

  • String Matching and 1d Lattice Gases. Mungan, Muhittin // Journal of Statistical Physics;Jan2007, Vol. 126 Issue 1, p207 

    We calculate the probability distribution for the number of occurrences n of a given l letter word x inside a random string of k letters, whose letters have been generated by a known stationary stochastic process. Denoting by p( x) the probability of occurrence of the word, it is well-known that...

  • Welfare and stability in senior matching markets. Cantala, David; Sánchez, Francisco // International Journal of Game Theory;2008, Vol. 36 Issue 3/4, p369 

    We consider matching markets at a senior level, where workers are assigned to firms at an unstable matching—the status-quo—which might not be Pareto efficient. It might also be that none of the matchings Pareto superior to the status-quo are Core stable. We propose two weakenings...

  • Cluster Integrated Updation Strategies for ACO Algorithms. Raghavendra, G. S.; Kumar, N. Prasanna // International Journal of Computer Applications;Sep2011, Vol. 30, p18 

    Ant Colony Optimization (ACO) algorithm has evolved as the most popular way to attack the combinatorial problems. The ACO algorithm employs multi agents called ants that are capable of finding optimal solution for a given problem instances. These ants at each step of the computation make...

  • THE STATIONARY SOLUTION OF A MULTISERVER QUEUING MODEL WITH DISCOURAGEMENT. Reynolds, John F. // Operations Research;Jan/Feb68, Vol. 16 Issue 1, p64 

    Several authors, including MORSE, ANCKER AND GAFARIAN, and COX AND SMITH have studied single-server queuing models in which the arrival rate is a decreasing function of queue length. This paper analyzes a multiserver generalization of the model given by Cox and Smith. A generating function is...

  • Power law distribution of seismic rates: theory and data analysis. Saichev, A.; Sornette, D. // European Physical Journal B -- Condensed Matter;Feb2006, Vol. 49 Issue 3, p377 

    We report an empirical determination of the probability density functions Pdata(r) (and its cumulative version) of the number r of earthquakes in finite space-time windows for the California catalog, over fixed spatial boxes 5 ×5 km2, 20 ×20 km2 and 50 ×50 km2 and time intervals...

  • Evaluation of the Stability of Underground Rock Pillars through a Probabilistic Approach. Guarascio, Massimo; Oreste, Pierpaolo // American Journal of Applied Sciences;Aug2012, Vol. 9 Issue 8, p1273 

    Problem statement: When the room and pillar mining method is adopted, the dimensioning of the rock pillars is one of the most important aspects that need to be faced from the engineering point of view. The available calculation methods are usually simplified and involve the areas of influence...

  • On the complex moments of symmetric power L-functions at s = 1. Cogdell, J.; Michel, P. // IMRN: International Mathematics Research Notices;2004, Vol. 2004 Issue 31, p1561 

    The study of the distribution values of L-functions at the point s = 1 is a classical topic in analytic number theory which goes back to Chowla and Erdös. For some time, this question has been limited to the case of Euler products of degree 1, and it is only recently that the case of...

  • An Efficient Algorithm for Exact Distribution of Discrete Scan Statistics. Ebneshahrashoob, Morteza; Gao, Tangan; Wu, Mengnien // Methodology & Computing in Applied Probability;Dec2005, Vol. 7 Issue 4, p459 

    Waiting time random variables and related scan statistics have a wide variety of interesting and useful applications. In this paper, exact distribution of discrete scan statistics for the cases of homogeneous two-state Markov dependent trials as well as i.i.d. Bernoulli trials are discussed by...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics