✦ LIBER ✦

On parallelizing recursive neural networks on coarse-grained parallel computers: A general algorithm

✍ Scribed by Antonio d'Acierno; Roberto Vaccaro

Book ID: 107919368
Publisher: Elsevier Science
Year: 1994
Tongue: English
Weight: 582 KB
Volume: 20
Category: Article
ISSN: 0167-8191
DOI: 10.1016/0167-8191(94)90084-1

No coin nor oath required. For personal study only.

📜 SIMILAR VOLUMES

Deterministic parallel selection algorit

Deterministic parallel selection algorithms on coarse-grained multicomputers

✍ M. Cafaro; Vincenzo De Bene; G. Aloisio 📂 Article 📅 2009 🏛 John Wiley and Sons 🌐 English ⚖ 351 KB

## Abstract We present two deterministic parallel Selection algorithms for distributed memory machines, under the coarse‐grained multicomputer model. Both are based on the use of two weighted 3‐medians, that allows discarding at least 1/3 of the elements in each iteration. The first algorithm sligh

An efficient coarse-grained parallel alg

An efficient coarse-grained parallel algorithm for global–local multiscale computations on massively parallel systems

✍ Rahul; Suvranu De 📂 Article 📅 2009 🏛 John Wiley and Sons 🌐 English ⚖ 545 KB

Optimizing neural networks on SIMD paral

Optimizing neural networks on SIMD parallel computers

✍ Andrea Di Blas; Arun Jagota; Richard Hughey 📂 Article 📅 2005 🏛 Elsevier Science 🌐 English ⚖ 417 KB

Connected Component Labeling on Coarse G

Connected Component Labeling on Coarse Grain Parallel Computers: An Experimental Study

✍ A. Choudhary; R. Thakur 📂 Article 📅 1994 🏛 Elsevier Science 🌐 English ⚖ 499 KB

Connected component labeling is a fundamental task in computer vision. This paper presents parallel implementations of connected component labeling for grey level images on the iPSC/2 and iPSC \(/ 860\) hypercubes, the CM-5, and on the shared memory Encore Multimax multiprocessor. Several partitioni

Cellular neural networks as a general ma

Cellular neural networks as a general massively parallel computational paradigm

✍ Destri, Giulio; Marenzoni, Paolo 📂 Article 📅 1996 🏛 John Wiley and Sons 🌐 English ⚖ 896 KB

In this paper is presented the use of the discrete-time cellular neural network (DTCNN) paradigm to develop algorithms devised for general-purpose massively parallel processing (MPP) systems. This paradigm is defined in discrete N-dimensional spaces (lattices) and is characterized by the locality of

On Estimating Machine Dependency of Fine

On Estimating Machine Dependency of Fine– and Coarse–Grained Parallel Structural Computations

✍ W. J. Watkins; D. Kennedy; F. W. Williams 📂 Article 📅 1997 🏛 John Wiley and Sons 🌐 English ⚖ 321 KB