Multilayer feedforward networks are universal approximators
Neural Networks
Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Learning higher order correlations
Neural Networks
Time Series Analysis: Forecasting and Control
Time Series Analysis: Forecasting and Control
Improved generalized neuron model for short-term load forecasting
Soft Computing - A Fusion of Foundations, Methodologies and Applications
IEEE Transactions on Neural Networks
Logic operations based on single neuron rational model
IEEE Transactions on Neural Networks
Approximation capability in C(R¯n) by multilayer feedforward networks and related problems
IEEE Transactions on Neural Networks
| Hi-index | 12.05 |
The paper proposes a new neuron model (geometric mean neuron model) with an aggregation function based on geometric mean of all inputs. Performance of the geometric mean neuron model was evaluated using various learning algorithms like the back-propagation and resilient propagation on various real life data sets. Comparison of the performance of this model was made with the performance of multilayer perceptron. It has been shown that the geometric mean based aggregation function with resilient propagation (RPROP) performs the best both in terms of accuracy and speed.