论文信息 - A multilayer feedforward neural network having N/4 nodes in two hidden layers

A multilayer feedforward neural network having N/4 nodes in two hidden layers

In order to reduce the complexity of a single hidden layer multilayer neural network, a new two hidden layer MFNN (THL-MFNN) with a combined structure of a RBFN and MLPs is proposed, and its associated training method is discussed. The proposed THL-MFNN can be easily constructed, and can be efficiently trained by online recursive methods. The performance of the proposed THL-MFNN with P/4+2=18 hidden nodes and 34 weights is equal to that of an optimum Bayesian equalizer using an RBFN with P=64 hidden nodes and 64 weights. The role of each layer in the proposed THL-MFNN is presented by a theoretical approach, and the feasibility of a more reduced structure is given.

Kyunbyoung Ko | Sooyong Choi | Daesik Hong

[1] Daesik Hong,et al. Nonlinear multilayer combining techniques for Bayesian equalizers using the radial basis function network as a digital magnetic storage equalizer , 1999 .

[2] Richard P. Lippmann,et al. An introduction to computing with neural nets , 1987 .

[3] G. J. Gibson,et al. On the decision regions of multilayer perceptrons , 1990, Proc. IEEE.

[4] Yih-Fang Huang,et al. Bounds on the number of hidden neurons in multilayer perceptrons , 1991, IEEE Trans. Neural Networks.

[5] R. Lippmann,et al. An introduction to computing with neural nets , 1987, IEEE ASSP Magazine.

[6] Sheng Chen,et al. A clustering technique for digital communications channel equalization using radial basis function networks , 1993, IEEE Trans. Neural Networks.

[7] Shin'ichi Tamura,et al. Capabilities of a four-layered feedforward neural network: four layers versus three , 1997, IEEE Trans. Neural Networks.