In this paper we describe the implementalion of the backpropagation aIgorilhm by means of an object oriented library (ARCH). The use of this library relieves the user from the details of a specific parallel programming machines and at the same time allows a greater portability oí the generated code. To provide a comparison with existing solutions, we survey the most relevant implementations oí the algorthm proposed so far in the lilerature, bolh on dedicaled and general purpose computers. Extensive experimental results show that the use of tbe library dos not hurt the performance of our simulator, on the contrary our implementation on a connection Machine (CM-S) is comparable wilh the fastest in its calegory.
Object Oriented Design of a Simulator for Large BP Neural Networks
ANGUITA, DAVIDE
1995
Abstract
In this paper we describe the implementalion of the backpropagation aIgorilhm by means of an object oriented library (ARCH). The use of this library relieves the user from the details of a specific parallel programming machines and at the same time allows a greater portability oí the generated code. To provide a comparison with existing solutions, we survey the most relevant implementations oí the algorthm proposed so far in the lilerature, bolh on dedicaled and general purpose computers. Extensive experimental results show that the use of tbe library dos not hurt the performance of our simulator, on the contrary our implementation on a connection Machine (CM-S) is comparable wilh the fastest in its calegory.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
