"425-430" . . "Design of optimal input signal for system modeled by multi-layer perceptron network is treated. Because the true system is unknown, the design can be constructed only from the actually obtained model. However, neural networks with the same structure differing only in parameters values are able to approximate various nonlinear mappings therefore it is crucial maximally to use available informations to select suitable input data. Hence a global estimation method allowing to determine conditional probability density functions of network parameters will be used. The Gaussian sum approach based on approximation of arbitrary probability density function by a sum of normal distributions seems to be suitable to use. This approach is a less computationally demanding alternative to the sequential Monte Carlo methods and gives better results than the commonly used prediction error methods. The properties of the proposed experimental design are demonstrated in a numerical example." . "2"^^ . . "Hering, Pavel" . . "6"^^ . . "System identification; optimal experiment design; nonlinear parameters estimation; probability density function; multi-layer perceptron network"@en . . "Gaussian Sum Approach with Optimal Experiment Design for Neural Network" . "Honolulu" . "Design of optimal input signal for system modeled by multi-layer perceptron network is treated. Because the true system is unknown, the design can be constructed only from the actually obtained model. However, neural networks with the same structure differing only in parameters values are able to approximate various nonlinear mappings therefore it is crucial maximally to use available informations to select suitable input data. Hence a global estimation method allowing to determine conditional probability density functions of network parameters will be used. The Gaussian sum approach based on approximation of arbitrary probability density function by a sum of normal distributions seems to be suitable to use. This approach is a less computationally demanding alternative to the sequential Monte Carlo methods and gives better results than the commonly used prediction error methods. The properties of the proposed experimental design are demonstrated in a numerical example."@en . . "Honolulu" . . "2"^^ . . "ACTA Press" . "RIV/49777513:23520/07:00000046" . . . "[4211FBBFE60D]" . "Gaussian Sum Approach with Optimal Experiment Design for Neural Network" . . . "978-0-88986-676-8" . . "Metoda Gaussov\u00FDch sm\u011Bs\u00ED p\u0159i n\u00E1vrhu optim\u00E1ln\u00EDho vstupn\u00EDho sign\u00E1lu neuronov\u00E9 s\u00EDt\u011B"@cs . "\u0160imandl, Miroslav" . "2007-01-01+01:00"^^ . . "Metoda Gaussov\u00FDch sm\u011Bs\u00ED p\u0159i n\u00E1vrhu optim\u00E1ln\u00EDho vstupn\u00EDho sign\u00E1lu neuronov\u00E9 s\u00EDt\u011B"@cs . "Gaussian Sum Approach with Optimal Experiment Design for Neural Network"@en . . . . "\u010Cl\u00E1nek se zab\u00FDv\u00E1 n\u00E1vrhem optim\u00E1ln\u00EDho vstupn\u00EDho sign\u00E1lu v \u00FAloze identifikace neline\u00E1rn\u00EDho stochastick\u00E9ho syst\u00E9mu neuronovou s\u00EDt\u00ED. Vstupn\u00ED sign\u00E1l je navr\u017Een na z\u00E1klad\u011B aktu\u00E1ln\u011B z\u00EDskan\u00E9ho modelu. Kl\u00ED\u010Dovou \u00FAlohu proto hraje vhodn\u00E1 metoda odhadu parametr\u016F. Navr\u017Een\u00E1 metoda generov\u00E1n\u00ED vstupn\u00EDho sign\u00E1lu vyu\u017E\u00EDv\u00E1 podm\u00EDn\u011Bn\u00FDch hustot pravd\u011Bpodobnosti parametr\u016F m\u00EDsto b\u011B\u017En\u011B u\u017E\u00EDvan\u00FDch bodov\u00FDch odhad\u016F. Z tohoto d\u016Fvodu byla k odhadu parametr\u016F s\u00EDt\u011B pou\u017Eita glob\u00E1ln\u00ED metoda Gaussov\u00FDch sm\u011Bs\u00ED. Navr\u017Een\u00E1 metoda umo\u017E\u0148uje l\u00E9pe poznat identifikovan\u00FD syst\u00E9m, ne\u017E pokud by byly pou\u017Eity st\u00E1vaj\u00EDc\u00ED metody n\u00E1vrhu vstupn\u00EDho sign\u00E1lu."@cs . "Gaussian Sum Approach with Optimal Experiment Design for Neural Network"@en . . "Proceedings of the Ninth IASTED International Conference on Signal and Image Processing" . "RIV/49777513:23520/07:00000046!RIV08-GA0-23520___" . "23520" . "422982" . . "P(GA102/05/2075), P(GP102/06/P202)" . .