✦ LIBER ✦

A parallel formulation of back-propagation learning on distributed memory multiprocessors

✍ Scribed by S. Mahapatra; R.N. Mahapatra; B.N. Chatterji

Publisher: Elsevier Science
Year: 1997
Tongue: English
Weight: 894 KB
Volume: 22
Category: Article
ISSN: 0167-8191
DOI: 10.1016/s0167-8191(96)00051-8

No coin nor oath required. For personal study only.

✦ Synopsis

This paper presents a mapping scheme for parallel pipelined execution of the Back-propagation Learning Algorithm on distributed memory multiprocessors.

The proposed implementation exhibits inter-layer or pipelined parallelism, unique to the multilayer neural networks. Simple algorithms have heen presented, which allow the data transfer involved in both recall and learning phases of the back-propagation algorithm to be carried out with a small communication overhead. The effectiveness of the mapping scheme has been illustrated, by estimating the speedup of the proposed implementation on an array of T-805 transputers.

📜 SIMILAR VOLUMES

A parallel block row-action method for s

A parallel block row-action method for solving large sparse linear systems on distributed memory multiprocessors

✍ D'apuzzo, Marco ;De Rosa, Maria Assunta 📂 Article 📅 1994 🏛 John Wiley and Sons 🌐 English ⚖ 767 KB

Parallelization of R-matrix propagation

Parallelization of R-matrix propagation methods on distributed memory computers

✍ A.G. Sunderland; J.W. Heggarty; C.J. Noble; N.S. Scott 📂 Article 📅 1998 🏛 Elsevier Science 🌐 English ⚖ 865 KB

The R-matrix and Logarithmic Derivative methods are numerically very stable and are therefore ideal for integrating the large sets of coupled second-order linear differential equations which arise in non-exchange scattering problems (e.g., electron scattering by atoms and molecules). These calculati

Parallel parsing of MPEG video on a shar

Parallel parsing of MPEG video on a shared-memory symmetric multiprocessor

✍ Suchendra M. Bhandarkar; Shankar R. Chandrasekaran 📂 Article 📅 2004 🏛 Elsevier Science 🌐 English ⚖ 744 KB

A study on initial value setting of the

A study on initial value setting of the back-propagation learning algorithm

✍ Qi Jia; Naohiro Toda; Shiro Usui 📂 Article 📅 1991 🏛 John Wiley and Sons 🌐 English ⚖ 574 KB

Efficient parallel implementation of the

Efficient parallel implementation of the hough transform on a distributed memory system

✍ D Ben-Tzvi; A Naqui; M Sandler 📂 Article 📅 1990 🏛 Elsevier Science ⚖ 78 KB

Normally, in parallel implementations of the Hough transform either the transform space or the set of image features can be distributed among the processing elements. A method is proposed to link parallel access to feature points in the image, and parallel access to the transform space. A synchronou

Numerical simulation of fluid dynamic pr

Numerical simulation of fluid dynamic problems on distributed memory parallel computers

✍ Pirozzi, Maria A. 📂 Article 📅 1997 🏛 John Wiley and Sons 🌐 English ⚖ 91 KB 👁 3 views

This paper describes the parallel implementation of a numerical model for the simulation of problems from fluid dynamics on distributed memory multiprocessors. The basic procedure is to apply a fully explicit upwind finite difference approximation on a staggered grid. A theoretical time complexity a