Artificial Neural Network Engine: Parallel and Parameterized Architecture Implemented in FPGA

13 years 9 months ago

Download www.research.rutgers.edu

In this paper we present and analyze an artificial neural network hardware engine, its architecture and implementation. The engine was designed to solve performance problems of the serial software implementations. It is based on a hierarchical parallel and parameterized architecture. Taking into account verification results, we conclude that this engine improves the computational performance, producing speedups from 52.3 to 204.5 and its architectural parameterization provides more flexibility.

Milene Barbosa Carvalho, Alexandre Marques Amaral,

Real-time Traffic

Network Hardware Engine | Parameterized Architecture | PREMI 2005 | Serial Software Implementations |

claim paper

» A highperformance FPGA architecture for restricted boltzmann machines

» Parallel hardware implementation of a broad class of spiking neurons using serial arithmet...

» FPGATargeted Neural Architecture for Embedded Alertness Detection

» A multiFPGA architecture for stochastic Restricted Boltzmann Machines

» FPGA Accelerated Simulation of Biologically Plausible Spiking Neural Networks

» A SIMD Neural Network Processor for Image Processing

» Methods for Parallelizing the Probabilistic Neural Network on a Beowulf Cluster Computer

» A symbolicsubsymbolic interface protocol for cognitive modeling

Post Info
More Details (n/a)

Added	28 Jun 2010
Updated	28 Jun 2010
Type	Conference
Year	2005
Where	PREMI
Authors	Milene Barbosa Carvalho, Alexandre Marques Amaral, Luiz Eduardo da Silva Ramos, Carlos Augusto Paiva da Silva Martins, Petr Ekel

Comments (0)

Sciweavers

Artificial Neural Network Engine: Parallel and Parameterized Architecture Implemented in FPGA

Network Hardware Engine | Parameterized Architecture | PREMI 2005 | Serial Software Implementations |

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers