Neural Chip SAND in online data processing of extensive air showers

The neural chip SAND (Simple Applicable Neural Device) was designed to accelerate computations of neural networks at a very low cost basis, due to the fact that only few peripheral chips are necessary to use the neural network chip in applications. Four SAND-chips were implemented on one PCI-board....

Full description

Saved in:
Bibliographic Details
Published in:Computer physics communications 2000-04, Vol.126 (1), p.63-66
Main Authors: Eppler, W., Fischer, T., Gemmeke, H., Chilingarian, A., Vardanyan, A.
Format: Article
Language:English
Subjects:
Cosmic ray physics
Neural chip
Neural network
PCI board
Trigger
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The neural chip SAND (Simple Applicable Neural Device) was designed to accelerate computations of neural networks at a very low cost basis, due to the fact that only few peripheral chips are necessary to use the neural network chip in applications. Four SAND-chips were implemented on one PCI-board. The board is highly usable for hardware triggers in particle physics. The performance of a SAND-PCI-board is 800 Mega Connections per Second due to four neuro-chips, each with four parallel 16 bit multipliers and 40 bit adders. SAND is able to implement feedforward neural networks with a maximum of 512 input neurons and three hidden layers. Kohonen feature maps and radial basis function networks may be also calculated. The application of the SAND-PCI-board is proposed for cosmic ray physics to allow online analysis of extensive air showers.
ISSN:0010-4655
1879-2944
DOI:10.1016/S0010-4655(99)00423-3