The Hypercube Neural Network Algorithm is a novel supervised method for classification. One hypercube is defined per class in the attribute space based on the training data. Each dimension of a hypercube is set to cover the full range of values in the class. The hypercube learning is therefore a rapid, one-shot form of learning. This paper presents three versions of the algorithm: hypercube wit...

This paper analyzes a product network generated from torus and hypercube networks known as Torus embedded hypercube scalable interconnection network suitable for parallel architecture. It is shown here that how good a Torus embedded Hypercube interconnection network can be compared to the existing Mesh embedded hypercube interconnection network with minor modifications in its architecture. A co...

In this paper we present how to reconfigure dynamically a complete binary tree in faulty hypercubes. First, we use a dynamic algorithm to reconfigure a complete binary tree of height h (h≥0) in an (h+1)-dimensional faulty hypercube. If there is a faulty node in the hypercube, both the dilation and congestion are 2 after reconfiguration. If there are two faulty nodes in the hypercube, both the d...

Efficient sampling strategies that scale with the size of the problem, computational budget, and users’ needs are essential for various sampling-based analyses, such as sensitivity and uncertainty analysis. In this study, we propose a new strategy, called Progressive Latin Hypercube Sampling (PLHS), which sequentially generates sample points while progressively preserving the distributional pro...

Parallel routing and diameter are two important issues in interconnection networks. The hypercube is one of the most popular interconnection networks for parallel systems due to its attractive properties such as low diameter and efficient parallel routing. The exchanged hypercube, which is a variant of the hypercube by removing some specific edges, remains several desirable properties of the hy...

Advantages of hypercube network and torus topology are used to derive an embedded architecture for product network known as torus embedded hypercube scalable interconnection network. This paper analyzes torus embedded hypercube network pertinent to parallel architecture. The network metrics are used to show how good embedded network can be designed for parallel computation. Network parameter an...

Efficient hypercube algorithms are developed for the following image transformations: shrinking, expanding, translation, rotation, and scaling. A 2k−step shrinking and expanding of a gray scale N×N image can be done in O (k) time on an N2 processor MIMD hypercube and in O (logN) time on an SIMD hypercube. Translation, rotation, and scaling of an N×N image take O (logN) time on an N2 processor h...