"Neural Networks; CUDA; Parallel Computing; Graphics Processing Units"@en . "RIV/68407700:21230/10:00177603!RIV11-MSM-21230___" . . . "2010-09-06+02:00"^^ . "Prague" . "The evolutionary algorithms work with large sets of individuals. In our case these individuals represent neural networks. The speed of evaluation of the networks is the very crucial factor because it affects the overall speed of the whole evolution process. In this paper we describe our implementation of the fully recurrent neural networks on the general-purpose graphics processing units. We are using the nVidia CUDA technology to accelerate the simulation of the population of the networks. We have created package for Wolfram Mathematica that provides interface to our accelerated simulator from high-level programming environment. Our library supports the client-server architecture, so you can run the simulations on dedicated CUDA-enabled computational server and process the results of the simulations on your desktop using the TCP/IP communication protocol. In this paper we present the results of the speedup experiments." . . . "2"^^ . . . "261587" . "Proceedings of the 7th EUROSIM Congress on Modelling and Simulation, Vol. 2: Full Papers" . "High-performance Implementation of Recurrent Neural Networks on Graphics Processing Units"@en . "2"^^ . "Department of Computer Science and Engineering, FEE, CTU in Prague" . "Z(MSM6840770012)" . "978-80-01-04589-3" . . . "Buk, Zden\u011Bk" . . "High-performance Implementation of Recurrent Neural Networks on Graphics Processing Units"@en . . . "RIV/68407700:21230/10:00177603" . "Praha" . "\u0160norek, Miroslav" . "21230" . "High-performance Implementation of Recurrent Neural Networks on Graphics Processing Units" . . . "The evolutionary algorithms work with large sets of individuals. In our case these individuals represent neural networks. The speed of evaluation of the networks is the very crucial factor because it affects the overall speed of the whole evolution process. In this paper we describe our implementation of the fully recurrent neural networks on the general-purpose graphics processing units. We are using the nVidia CUDA technology to accelerate the simulation of the population of the networks. We have created package for Wolfram Mathematica that provides interface to our accelerated simulator from high-level programming environment. Our library supports the client-server architecture, so you can run the simulations on dedicated CUDA-enabled computational server and process the results of the simulations on your desktop using the TCP/IP communication protocol. In this paper we present the results of the speedup experiments."@en . . . "[3797BEC11682]" . "4"^^ . . . "High-performance Implementation of Recurrent Neural Networks on Graphics Processing Units" . .