Back to Search
Start Over
Periodic activation function and a modified learning algorithm for the multivalued neuron
- Source :
- IEEE transactions on neural networks. 21(12)
- Publication Year :
- 2010
-
Abstract
- In this paper, we consider a new periodic activation function for the multivalued neuron (MVN). The MVN is a neuron with complex-valued weights and inputs/output, which are located on the unit circle. Although the MVN outperforms many other neurons and MVN-based neural networks have shown their high potential, the MVN still has a limited capability of learning highly nonlinear functions. A periodic activation function, which is introduced in this paper, makes it possible to learn nonlinearly separable problems and non-threshold multiple-valued functions using a single multivalued neuron. We call this neuron a multivalued neuron with a periodic activation function (MVN-P). The MVN-Ps functionality is much higher than that of the regular MVN. The MVN-P is more efficient in solving various classification problems. A learning algorithm based on the error-correction rule for the MVN-P is also presented. It is shown that a single MVN-P can easily learn and solve those benchmark classification problems that were considered unsolvable using a single neuron. It is also shown that a universal binary neuron, which can learn nonlinearly separable Boolean functions, and a regular MVN are particular cases of the MVN-P.
- Subjects :
- Input/output
Artificial neural network
Databases, Factual
Computer Networks and Communications
Multivalued function
Activation function
General Medicine
Computer Science Applications
Periodic function
Support vector machine
Unit circle
Nonlinear Dynamics
Artificial Intelligence
Neural Networks, Computer
Boolean function
Algorithm
Software
Algorithms
Mathematics
Subjects
Details
- ISSN :
- 19410093
- Volume :
- 21
- Issue :
- 12
- Database :
- OpenAIRE
- Journal :
- IEEE transactions on neural networks
- Accession number :
- edsair.doi.dedup.....52486baa4cb419cb2429ba8b85aca98d