Complex generalized-mean neuron model and its applications

Tripathi, Bipin Kumar; Chandra, B.; Singh, Menakshi; Kalra, Prem Kumar

doi:10.1016/j.asoc.2009.12.038

Cited by 21 publications

(10 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [3,31,32], various neuron models based on the concept of generalized mean of all inputs (GMN) and their training algorithms have been discussed. The generalized mean (GM) [5] of N numbers can be defined as in (2), where ݃ is a real number and the value of gives the various mean as in Table I.…”

Section: Generalized Mean Single Multiplicative Neuron (Gmsmn) Modelmentioning

confidence: 99%

“…This problem can be solved by using a polynomial architecture as a non-linear aggregation function of the neuron model [2,3,27,28,31,32]. In [3,27,28,31,32], various neuron models based on the concept of generalized mean of all inputs (GMN) and their training algorithms have been discussed. These neuron models include an aggregation function based on the concept of generalized mean of all inputs.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Single multiplicative neuron model based on generalized mean

Attia

Sallam

Fahmy

2012

2012 Seventh International Conference on Computer Engineering &Amp; Systems (ICCES)

View full text Add to dashboard Cite

This paper presents a single multiplicative neuron model based on a polynomial architecture. The proposed neuron model consists of a non-linear aggregation function based on the concept of generalized mean of all multiplicative inputs. This neuron model has the same number of parameters as the single multiplicative neuron model (SMN). The SMN model is a special case of the proposed generalized mean single multiplicative neuron (GMSMN) model. The structure of this model is simpler than higher-order neuron model. The simulation results show that the performance of the proposed neuron model is better than SMN model.

show abstract

Section: Generalized Mean Single Multiplicative Neuron (Gmsmn) Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Single multiplicative neuron model based on generalized mean

Attia

Sallam

Fahmy

2012

2012 Seventh International Conference on Computer Engineering &Amp; Systems (ICCES)

View full text Add to dashboard Cite

show abstract

“…The main motivation to use CVNNs is due to faster convergence, reduction in learning parameters, and ability to learn two dimension motion of signal in complex-valued neural network. 21 The CVNNs are simply the generalization of the real valued neural networks in the complex valued domain, where all the parameters including weights, biases, inputs, and outputs could be complex variables.…”

Section: Introductionmentioning

confidence: 99%

Complex-valued forecasting of the global solar irradiation

Saoud

Rahmoune

Tourtchine

et al. 2013

Journal of Renewable and Sustainable Energy

View full text Add to dashboard Cite

In this paper, a forecasting of the global solar irradiation in the complex-valued domain is proposed. A method to transform the meteorological data into complex values is developed and the Complex Valued Neural Network (CVNN) is used to model and forecast the daily and the hourly solar irradiation. The measured data of Tamanrasset city, Algeria (altitude: 1362 m; latitude: 22 48 N; longitude: 05 26 E) is used to validate the developed model. In the hourly solar irradiation case, the 24 h ahead will be forecasted using the combination of the past daily meteorological dataset. Several models are presented to test the feasibility and the performance of the CVNN for forecasting either daily or hourly solar irradiation for both multi input single output and multi input multi output strategies. Results obtained throughout this paper show that the CVNN technique is suitable for modeling and forecasting daily and hourly solar irradiation. V C 2013 AIP Publishing LLC.

show abstract

“…Thus, it is more significant in problems, where we wish to learn and analyze signal amplitude and phase precisely. Complex-valued neural networks (CVNN) has been found worth while in recent researches to provide efficient solution for problems in single dimension as well as on plane [7], [8], [9]. Moreover, the better degree of accuracy is achieved with a smaller network topology.…”

Section: Introductionmentioning

confidence: 99%

“…In order to have the higher order non-linear correlation among input patterns, extensive attempts have been made by Giles and Maxwell (1987), Xu et al (1992), Zhang et al (2002), Homma et al (2003) and Kalra et al (2003) to develop the higher order neurons. Motivated by their efforts, a class of structures known as pi-sigma [12], [13], second order neuron [14], generalized neurons [15], [16], [9] and other higher order neurons [17], [18] and functional link networks [19], [20] have been introduced. Though, higher order neurons have proved to be most efficient, but they suffer from the typical curse of dimensionality due to combinatorial explosion of terms, demanding sparseness in the represen tation.…”

Section: Introductionmentioning

confidence: 99%

Functional mapping with complex higher order compensatory neuron model

Tripathi

Kalra

2010

The 2010 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

The basic ideas to develop artificial neural net work (ANN) were originated with the investigation of brain's micro-structure. It has been a steady endeavor in the research that followed to develop it further and integrate additional discoveries about the human brain with a view to evolve the artificial neuron model closer to the actual brain functioning.The pursuit has ever been on to replicate the typical charac teristic of the neuron. The neuron response to the input signals impinged onto it, is defined how they are aggregated with in the unit. A substantial body of evidence has grown to support the presence of non-linear integration of synaptic inputs in the neuron cells. Superior functionality of ANN in complex domain has been observed in recent researches, which presented the second generation of development in ANN. In this paper, we explore the functional capabilities of a compensatory neuron model with complex-valued high order non-linear aggregation function. The strength and effectiveness of considered neuron is evaluated with an efficient learning algorithm in a complex domain. The performance analysis is carried out through a solid set of simulations. B K Tripathi is with the

show abstract

Complex generalized-mean neuron model and its applications

Cited by 21 publications

References 10 publications

Single multiplicative neuron model based on generalized mean

Single multiplicative neuron model based on generalized mean

Complex-valued forecasting of the global solar irradiation

Functional mapping with complex higher order compensatory neuron model

Contact Info

Product

Resources

About