Attractor neural networks such as the Hop eld network can be trained by a number of algorithms. The simplest of these methods is the Hebb rule which is strictly local (the weight of the synapse depends only on the activation of the two neurons it connects) and incremental (adding a new memory can be done knowing only the old weight matrix and not the actual patterns previously stored). Both of ...

Distance measures like the Euclidean distance have been the most widely used to measure similarities between feature vectors in the content-based image retrieval (CBIR) systems. However, in these similarity measures no assumption is made about the probability distributions and the local relevances of the feature vectors. Therefore, irrelevant features might hurt retrieval performance. Probabili...

Optical character recognition is undoubtedly considered as a one of the most active and dynamic fields of pattern recognition and artificial intelligence; it really provides in fact a solution for recognizing large volume of patterns automatically. The purpose of the present study is to compare in one hand between the performances of three novel hybrid methods used in OCR for extracting efficie...

The aim of this paper is to generalize the‎‎notion of pseudo-almost valuation domains to arbitrary‎ ‎commutative rings‎. ‎It is shown that the classes of chained rings‎ ‎and pseudo-valuation rings are properly contained in the class of‎ ‎pseudo-almost valuation rings; also the class of pseudo-almost‎ ‎valuation rings is properly contained in the class of quasi-local‎ ‎rings with linearly ordere...

Our participation to ImageCLEFphoto07, for the first time, was motivated by assessing several transmedia similarity measures that we recently designed and developed. The object of investigation consists here in some “intermediate level” fusion approaches, where we use some principles coming from pseudo-relevance feedback and, more specifically, use transmedia pseudo-relevance feedback for enric...

 ABRIR at NTCIR-8 Approach C t ti f N d E tit d t b Construction of Boolean query by using pseudo relevant documents Named entity is more important than others Verb synonym list is used for increasing coverage Combination of Boolean IR model and probabilistic IR model (Okapi) Penalty is applied for documents that don’t satisfy Boolean query Named entity is more important than others  F...

Let Gn be the subgroup of elements of odd order in the group Zn and let U(Gn) be the uniform probability distribution on Gn. In this paper, we establish a probabilistic polynomial-time reduction from finding a nontrivial divisor of a composite number n to finding a nontrivial relation between elements chosen independently and uniformly at random from Gn. Assume that finding a nontrivial divisor...

We present here some transmedia similarity measures that we recently designed by adopting some “intermediate level” fusion approaches. The main idea is to use some principles coming from pseudorelevance feedback and, more specifically, transmedia pseudo-relevance feedback for enriching the mono-media representation of an object with features coming from the other media. One issue that arises wh...

We present several results on the complexity of various forms of Sperner’s Lemma. In the black-box model of computing, we exhibit a deterministic algorithm for Sperner problems over pseudo-manifolds of arbitrary dimension. The query complexity of our algorithm is essentially linear in the separation number of the skeleton graph of the manifold and the size of its boundary. As a corollary we get...