Global Optimisation of Neural Networks Using a Deterministic Hybrid Approach [chapter]

Gleb Beliakov, Ajith Abraham
2002 Hybrid Information Systems  
Selection of the topology of a neural network and correct parameters for the learning algorithm is a tedious task for designing an optimal artificial neural network, which is smaller, faster and with a better generalization performance. In this paper we introduce a recently developed cutting angle method (a deterministic technique) for global optimization of connection weights. Neural networks are initially trained using the cutting angle method and later the learning is fine-tuned
more » ... g) using conventional gradient descent or other optimization techniques. Experiments were carried out on three time series benchmarks and a comparison was done using evolutionary neural networks. Our preliminary experimentation results show that the proposed deterministic approach could provide near optimal results much faster than the evolutionary approach.
doi:10.1007/978-3-7908-1782-9_8 fatcat:etyuvlv54fbkngk7b6vfscbhqq