Microsoft Word - 10001.rtf
نویسنده
چکیده
This paper reports work done to improve the modeling of complex processes when only small experimental data sets are available. Neural networks are used to capture the nonlinear underlying phenomena contained in the data set and to partly eliminate the burden of having to specify completely the structure of the model. Two different types of neural networks were used for the application of Pulping of Sugar Maple problem. A three layer feed forward neural networks, using the Preconditioned Conjugate Gradient (PCG) methods were used in this investigation. Preconditioning is a method to improve convergence by lowering the condition number and increasing the eigenvalues clustering. The idea is to solve the modified problem where M is a positive-definite preconditioner that is closely related to A. We mainly focused on Preconditioned Conjugate Gradientbased training methods which originated from optimization theory, namely Preconditioned Conjugate Gradient with Fletcher-Reeves Update (PCGF), Preconditioned Conjugate Gradient with Polak-Ribiere Update (PCGP) and Preconditioned Conjugate Gradient with PowellBeale Restarts (PCGB). The behavior of the PCG methods in the simulations proved to be robust against phenomenon such as oscillations due to large step size. b M Ax M 1 1 Keywords—Convergence, Modeling, Neural Networks, Preconditioned Conjugate Gradient
منابع مشابه
Microsoft Word - 10001.rtf
We discuss the application of matching in the area of resource discovery and resource allocation in grid computing. We present a formal definition of matchmaking, overview algorithms to evaluate different matchmaking expressions, and develop a matchmaking service for an intelligent grid environment. Keywords—Grid, Matchmaking, Ontology
متن کاملGolden - Trail : Retrieving the Data History that Matters from a
The 7 th International Digital Curation Conference will be taking place 5-7 December 2011 in Bristol. Please ensure you use the guidance in this template to produce your paper. Please submit your paper in one of the following formats: Microsoft Word (.doc), Open Office (.odt) or Rich Text (.rtf).
متن کاملMicrosoft Word - intermag_REVISED_submitted_Nov_04.rtf
System Overview We consider an iterative decoding and detection system for magnetic recording channels. The system uses a zero-forcing equalizer to shape the channel response to a target polynomial, called a partial-response (PR) polynomial. We assume that the noise at the input to the equalizer is AWGN. Hence, noise enhancement and coloration occur at the output of the equalizer. The output of...
متن کاملSpeech Recognition Software and Vidispine
To evaluate libraries for continuous speech recognition, a test based on TED-talk videos was created. The different speech recognition libraries PocketSphinx, Dragon NaturallySpeaking and Microsoft Speech API were part of the evaluation. From the words that the libraries recognized, Word Error Rate (WER) was calculated and the results show that Microsoft SAPI performed worst with a WER of 60.8%...
متن کامل