Modeling with Recurrent Neural Networks using Generalized Mean Neuron Model
Gunjan Gupta, Ram Narayan Yadav, Prem Kumar Kalra, Jisha John · 2005
This paper presents the use of generalized mean neuron model (GMN) in recurrent neural networks (RNNs). The GMN includes a new aggregation function based on the concept of generalized mean of all the inputs to the neuron. Learning is implemented on-line, based on input-output data using an alternative approach to recurrent back- propagation learning algorithm. The learning and generalization capabilities of the proposed model with RNNs have been tested and compared with that of multilayer perceptrons (MLPs). The simulation results show that the proposed model performs significantly better than the existing MLP when used in RNNs.