Generalized Power Mean Neuron Model

The paper proposes a novel neuron model termed as Generalized Power Mean Neuron model (GPMN). The paper focuses on illustrating the computational power and the generalization capability of this model. In this model, the aggregation function is based on generalized power mean of the inputs. The performance of the neural network using GPMN model is compared with traditional feed-forward neural network on several benchmark classification problems. It has been shown that the neural network using GPMN model performs far superior compared to the traditional feed-forward neural network both in terms of accuracy and speed.

[1]  Devendra K. Chaturvedi,et al.  Improved generalized neuron model for short-term load forecasting , 2004, Soft Comput..

[2]  Hsu-Tung Ku,et al.  GENERALIZED POWER MEANS AND INTERPOLATING INEQUALITIES , 1999 .

[3]  Prem Kumar Kalra,et al.  New Neuron Model for Blind Source Separation , 2009, ICONIP.

[4]  T A Plate,et al.  Randomly connected sigma–pi neurons can form associator networks , 2000, Network.

[5]  Michael Schmitt,et al.  On the Complexity of Computing and Learning with Multiplicative Neural Networks , 2002, Neural Computation.

[6]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[7]  Colin Giles,et al.  Learning, invariance, and generalization in high-order neural networks. , 1987, Applied optics.

[8]  Prem Kumar Kalra,et al.  Learning of new neuron model based on geometric mean with new error metrics , 2008, 2008 IEEE International Conference on Systems, Man and Cybernetics.

[9]  Tin Kam Ho,et al.  The learning behavior of single neuron classifiers on linearly separable or nonseparable input , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[10]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[11]  Richard Labib,et al.  New single neuron structure for solving nonlinear problems , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[12]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[13]  Meng Wang,et al.  Logic operations based on single neuron rational model , 2000, IEEE Trans. Neural Networks Learn. Syst..

[14]  P. Bullen.  Handbook of means and their inequalities , 1987 .

[15]  Prem Kumar Kalra,et al.  Some new neural network architectures with improved learning schemes , 2000, Soft Comput..

[16]  Stephen Coombes,et al.  Learning higher order correlations , 1993, Neural Networks.