Synthesis of Sigma-Pi Neural Networks by the Breeder Genetic Programming
نویسندگان
چکیده
Genetic programming has been successfully ap plied to evolve computer programs for solving a variety of interesting problems In the previous work we introduced the breeder genetic programming BGP method that has Occam s razor in its tness measure to evolve minimal size multilayer perceptrons In this paper we apply the method to synthesis of sigma pi neural networks Unlike percep tron architectures sigma pi networks use product units as well as summation units to build higher order terms The e ectiveness of the method is demonstrated on benchmark problems Simulation results on noisy data suggest that BGP not only improves the generalization performance it can also accelerate the convergence speed
منابع مشابه
Estimation of Discharge over the Submerged Compound Sharp-Crested Weir using Artificial Neural Networks and Genetic Programming
Truncated sharp crested weirs are used to measure flow rate and control upstream water surface in irrigation canals and laboratory flumes. The main advantages of such weirs are ease of construction and capability of measuring a wide range of flows with sufficient accuracy. Artificial neural networks (ANNs) and genetic programming (GP) have recently been used for estimation of hydraulic data. In...
متن کاملBalancing Accuracy and Parsimony in
Genetic programming is distinguished from other evolutionary algorithms in that it uses tree representations of variable size instead of linear strings of xed length. The exible representation scheme is very important because it allows the underlying structure of the data to be discovered automatically. One primary diiculty, however, is that the solutions may grow too big without any improvemen...
متن کاملDevelopment and Performance Evaluation of Adaptive Hybrid Higher Order Neural Networks for Exchange Rate Prediction
Higher Order Neural Networks (HONN) are characterized with fast learning abilities, stronger approximation, greater storage capacity, higher fault tolerance capability and powerful mapping of single layer trainable weights. Since higher order terms are introduced, they provide nonlinear decision boundaries, hence offering better classification capability as compared to linear neuron. Nature-ins...
متن کاملNeural Network Sensitivity to Inputs and Weights and its Application to Functional Identification of Robotics Manipulators
Neural networks are applied to the system identification problems using adaptive algorithms for either parameter or functional estimation of dynamic systems. In this paper the neural networks' sensitivity to input values and connections' weights, is studied. The Reduction-Sigmoid-Amplification (RSA) neurons are introduced and four different models of neural network architecture are proposed and...
متن کاملBalancing Accuracy and Parsimony in Genetic Programming
Genetic programming is distinguished from other evolutionary algorithms in that it uses tree representa tions of variable size instead of linear strings of xed length The exible representation scheme is very important because it allows the underlying structure of the data to be discovered automatically One primary di culty however is that the solutions may grow too big without any improvement o...
متن کامل