Bounds on the number of samples needed for neural learning.

The relationship between the number of hidden nodes in a neural network, the complexity of a multiclass discrimination problem, and the number of samples needed for effect learning are discussed. Bounds for the number of samples needed for effect learning are given. It is shown that Omega(min (d,n) M) boundary samples are required for successful classification of M clusters of samples using a two-hidden-layer neural network with d-dimensional inputs and n nodes in the first hidden layer.     

Dynamic slack allocation algorithms for energy minimization on parallel machines

We explore novel algorithms for DVS (Dynamic Voltage Scaling) based energy minimization of DAG (Directed Acyclic Graph) based applications on parallel and distributed machines in dynamic environments. Static DVS algorithms for DAG execution use the estimated execution time. The estimated time in practice is overestimated or underestimated. Therefore, many tasks may be completed earlier or later than expected during the actual execution. For overestimation, the extra available slack can be added to future tasks so that energy requirements can be reduced. For underestimation, the increased time may cause the application to miss the deadline. Slack can be reduced for future tasks to reduce the possibility of not missing the deadline. In this paper, we present novel dynamic scheduling algorithms for reallocating the slack for future tasks to reduce energy and/or satisfy deadline constraints. Experimental results show that our algorithms are comparable to static algorithms applied at runtime in terms of energy minimization and deadline satisfaction, but require considerably smaller computational overhead.     

Parallel construction of multidimensional binary search trees

Multidimensional binary search tree (abbreviated k-d tree) is a popular data structure for the organization and manipulation of spatial data. The data structure is useful in several applications including graph partitioning, hierarchical applications such as molecular dynamics and n-body simulations, and databases. In this paper, we study efficient parallel construction of k-d trees on coarse-grained distributed memory parallel computers. We consider several algorithms for parallel k-d tree construction and analyze them theoretically and experimentally, with a view towards identifying the algorithms that are practically efficient. We have carried out detailed implementations of all the algorithms discussed on the CM-5 and report on experimental results     

The special role of rimes in the description, use, and acquisition of English orthography.

The links between spellings and sounds in a large set of English words with consonant–vowel–consonant phonological structure were examined. Orthographic rimes, or units consisting of a vowel grapheme and a final consonant grapheme, had more stable pronunciations than either individual vowels or initial consonant-plus-vowel units. In 2 large-scale studies of word pronunciation, the consistency of pronunciation of the orthographic rime accounted for variance in latencies and errors beyond that contributed by the consistency of pronunciation of the individual graphemes and by other factors. In 3 experiments, as well, children and adults made more errors on words with less consistently pronounced orthographic rimes than on words with more consistently pronounced orthographic rimes. Relations between spellings and sounds in the simple monomorphemic words of English are more predictable when the level of onsets and rimes is taken into account than when only graphemes and phonemes are considered. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

PACK/UNPACK on Coarse-Grained Distributed Memory Parallel Machines

PACK/UNPACK are Fortran 90/HPF array construction functions that derive new arrays from existing arrays. We present algorithms for performing these operations on coarse-grained parallel machines. Our algorithms are relatively architecture independent and can be applied to arrays of arbitrary dimensions with arbitrary distribution along every dimension. Experimental results are presented on the CM-5.     

Runtime Support for Parallelization of Data-Parallel Applications on Adaptive and Nonuniform Computational Environments

In this paper we discuss the runtime support required for the parallelization of unstructured data-parallel applications on nonuniform and adaptive environments. We describe several optimization techniques for fast remapping of data and for reducing the amount of communications between machines when the computational load on the machines changes during the execution of data-parallel applications. The approach presented is reasonably general and is applicable to a wide variety of regular as well as irregular applications. We present performance results for the solution of an unstructured mesh on a cluster of workstations.     

Computing Hough transforms on hypercube multicomputers

Efficient algorithms to compute the Hough transform on MIMD and SIMD hypercube multicomputer are developed. Our algorithms can compute p angles of the Hough transform of an N × N image, p N, in 0(p + log N) time on both MIMD and SIMD hypercubes. These algorithms require 0(N ²) processors. We also consider the computation of the Hough transform on MIMD hypercubes with a fixed number of processors. Experimental results on an NCUBE/7 hypercube are presented.This research was supported by the National Science Foundation under grants DCR84-20935 and 86-17374. All correspondence should be mailed to Sanjay Ranka.     

Effects of polymer molecular weight and chemical modification on the gas transport properties of poly(2,6‐dimethyl‐1,4‐phenylene oxide)

Poly(2,6‐dimethyl‐1,4‐phenylene oxide) (PPO) of different intrinsic viscosities has been studied to understand the effect of polymer molecular weight on the permeability and permeability ratio of CO₂/CH₄ and O₂/N₂ gas pairs. The increase in permeability of dense films prepared from higher molecular weight PPO was explained in terms of increased free volume. Gas permeability for the high molecular weight was further improved by attaching bulky bromine groups to the phenyl ring of the PPO backbone. Permeability ratio of PPO was greatly improved by attaching polar groups such as —COOH or —SO₃H. The loss in permeability because of the presence of the polar groups was compensated by using PPO that was brominated and sulfonated. © 2000 John Wiley & Sons, Inc. J Appl Polym Sci 77: 1137–1143, 2000     

Benchmarking the computation and communication performance of the CM-5

Thinking Machines' CM-5 machine is a distributed-memory, message-passing computer. In the paper we devise a performance benchmark for the base and vector units and the data communication networks of the CM-5 machine. We model the communication characteristics such as communication latency and bandwidths of point-to-point and global communication primitives. We show, on a simple Gaussian elimination code, that an accurate static performance estimation of parallel algorithms is possible by using those basic machine properties connected with computation, vectorization, communication and synchronization. Futhermore, we describe the embedding of meshes or hypercubes on the CM-5 fat-tree topology and illustrate the performance results of their basic communication primitives.     

An improved algorithm for neural network classification ofimbalanced training sets

The backpropagation algorithm converges very slowly for two-class problems in which most of the exemplars belong to one dominant class. An analysis shows that this occurs because the computed net error gradient vector is dominated by the bigger class so much that the net error for the exemplars in the smaller class increases significantly in the initial iteration. The subsequent rate of convergence of the net error is very low. A modified technique for calculating a direction in weight-space which decreases the error for each class is presented. Using this algorithm, the rate of learning for two-class classification problems is accelerated by an order of magnitude.