Bilinear recurrent neural network

2009 International Conference on Computer Engineering and Technology

2009

A time-series prediction model using a Bilinear Recurrent Neural Network (BRNN) is proposed in this paper. The BRNN model used in this paper is the Multiresolution architecture with an adaptive training mode. The Multiresolution Bilinear Recurrent Neural Network (MBRNN) is based on the BLRNN that has been proven to have robust abilities in modeling and predicting time series. The proposed MBRNNbased predictor is applied to real-time MPEG video traffic data. The performance of the proposed MBRNN-based predictor is evaluated and compared with the conventional MultiLayer Perceptron Type Neural Network (MLPNN)-based predictor and BRNN-based predictor. When compared with the MLPNNbased predictor and the BRNN-based predictor, the proposed MBRNN-based predictor shows significant improvement in terms of the Normalized Mean Square Error (NMSE) criterion.

“…The model was initially proposed by Park and Zhu [11]. It has been successfully applied in modeling time-series data [11], [10].…”

Section: Bilinear Recurrent Neural Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of MPEG Traffic Data Using a Bilinear Recurrent Neural Network with Adaptive Training

2009 International Conference on Computer Engineering and Technology

2009

“…T represents the transpose of a matrix. More detailed information on BLRNN can be found in [19], [21]. If f (·) is the activation function of neurons, the output is given by:…”

Section: Bilinear Recurrent Neural Networkmentioning

confidence: 99%

Prediction of Sunspot Series Using BiLinear Recurrent Neural Network

2009 International Conference on Information Management and Engineering

Woo

2009

A prediction scheme of sunspot series using a BiLinear Recurrent Neural Network (BLRNN) is proposed in this paper. Since the BLRNN is based on the bilinear polynomial, it has been successfully used in modeling highly nonlinear systems with time-series characteristics and the BLRNN can be a natural choice in predicting sunspot series. The performance of the proposed BLRNN-based predictor is evaluated and compared with the conventional MultiLayerPerceptron Type Neural Network (MLPNN)-based predictor. Experiments are conducted on the Wolf sunspot series number data. The results show that the proposed BLRNNbased predictor outperforms the MLPNN-based one in terms of the Normalized Mean Squared Error (NMSE).

“…However, the MultiLayered type Neural Network(MLPNN) does not provide to accurate results in several occasions when time-series tendency is stronger than the regression components in time series data. A recurrent type neural network called Bilinear Recurrent Neural Network has been introduced [11]- [12]. Since the BRNN is based on a bilinear polynomial with recurrent elements, it has been more effectively used in modeling highly nonlinear systems with time-series characteristics and predicting time series data.…”

Section: Introductionmentioning

confidence: 99%

Sunspot series prediction using adaptively trained Multiscale-Bilinear Recurrent Neural Network

2011 9th IEEE/ACS International Conference on Computer Systems and Applications (AICCSA)

2011

A prediction scheme for sunspot series using a Recurrent Neural Network is proposed in this paper. The recurrent neural network adopted in this scheme is the MultiscaleBilinear Recurrent Neural Network with an adaptive learning algorithm (M-BRNN (AL)). The M-BLRNN(AL) is formulated by a combination of several Bilinear Recurrent Neural Network (BRNN) models in which each model is employed for predicting the signal at a certain level obtained by a wavelet transform. The learning process is further improved by applying an adaptive learning algorithm at each resolution level. In order to evaluate the performance of the proposed M-BRNN(AL)-based predictor, experiments are conducted on the Wolf sunspot series number data and the resulting prediction accuracy is compared with those of conventional MultiLayer Perceptron Type Neural Network (MLPNN)-based and BRNN-based predictors. The results show that the proposed M-BRNN(AL)-based predictor outperforms the MLPNN-based and BRNN-based predictors in terms of the Normalized Mean Squared Error (NMSE).