Practical, Computation Efficient High-Order Neural Network for Rotation and Shift Invariant Pattern Recognition

In this paper, a modification for the high-order neural network (HONN) is presented. Third order networks are considered for achieving translation, rotation and scale invariant pattern recognition. They require however much storage and computation power for the task. The proposed modified HONN takes into account a priori knowledge of the binary patterns that have to be learned, achieving significant gain in computation time and memory requirements. This modification enables the efficient computation of HONNs for image fields of greater that 100 × 100 pixels without any loss of pattern information.

Bulgariana: A Bulgarian Aggregator to Europeana

Europeana is the European virtual museum which was established in 2008. Its ambition is to create a common space allowing to access the cultural heritage of Europe from a single portal, by creating a network in all European countries. To make the initiative technically possible, Europeana has built a technological infrastructure to aggregate metadata from the different Europeana countries and memory institutions, while keeping the original digitized content on their sites. This paper presents Bulgariana, the Bulgarian chapter of Europeana. It is part of the technical infrastructure of Europeana, an established technical aggregator of Bulgarian cultural heritage content. It uses the two Europeana representation models ESE and EDM. Bulgariana is also a community building initiative putting in place a Bulgarian wide network of professionals and institutions working together to preserve and present Bulgarian cultural heritage around the world.

Plaintext Recovery in DES-like Cryptosystems Based on S-boxes with Embedded Parity Check

We describe an approach for recovering the plaintext in block ciphers having a design structure similar to the Data Encryption Standard but with improperly constructed S-boxes. The experiments with a backtracking search algorithm performing this kind of attack against modified DES/Triple-DES in ECB mode show that the unknown plaintext can be recovered with a small amount of uncertainty and this algorithm is highly efficient both in time and memory costs for plaintext sources with relatively low entropy. Our investigations demonstrate once again that modifications resulting to S-boxes which still satisfy some design criteria may lead to very weak ciphers. ACM Computing Classification System (1998): E.3, I.2.7, I.2.8.