Multilayer feedforward networks are universal approximators
Neural Networks
The Strength of Weak Learnability
Machine Learning
The cascade-correlation learning architecture
Advances in neural information processing systems 2
Modeling with constructive backpropagation
Neural Networks
Neural Computation
Capabilities of a four-layered feedforward neural network: four layers versus three
IEEE Transactions on Neural Networks
IEEE Transactions on Neural Networks
Fast initialization for cascade-correlation learning
IEEE Transactions on Neural Networks
Exploring constructive cascade networks
IEEE Transactions on Neural Networks
Modified cascade-correlation learning for classification
IEEE Transactions on Neural Networks
Constructive feedforward neural networks using Hermite polynomial activation functions
IEEE Transactions on Neural Networks
Use of a quasi-Newton method in a feedforward neural network construction algorithm
IEEE Transactions on Neural Networks
| Hi-index | 0.00 |
This paper presents a new constructive algorithm, called problem dependent constructive algorithm (PDCA), for designing and training artificial neural networks (ANNs). Unlike most previous studies, PDCA puts emphasis on architectural adaptation as well as function level adaptation. The architectural adaptation is done by determining automatically the number of hidden layers in an ANN and of neurons in hidden layers. The function level adaptation, is done by training each hidden neuron with a different training set. PDCA uses a constructive approach to achieve both the architectural as well as function level adaptation. It has been tested on a number of benchmark classification problems in machine learning and ANNs. The experimental results show that PDCA can produce ANNs with good generalization ability in comparison with other algorithms.