Distributed differential evolution with explorative---exploitative population families
Genetic Programming and Evolvable Machines
Parallel global optimisation meta-heuristics using an asynchronous island-model
CEC'09 Proceedings of the Eleventh conference on Congress on Evolutionary Computation
A Lamarckian Hybrid of Differential Evolution and Conjugate Gradients for Neural Network Training
Neural Processing Letters
On the impact of the migration topology on the Island Model
Parallel Computing
Two algorithmic enhancements for the parallel differential evolution
International Journal of Innovative Computing and Applications
A study on scale factor in distributed differential evolution
Information Sciences: an International Journal
Parallel random injection differential evolution
EvoApplicatons'10 Proceedings of the 2010 international conference on Applications of Evolutionary Computation - Volume Part I
A study on scale factor/crossover interaction in distributed differential evolution
Artificial Intelligence Review
Information Sciences: an International Journal
Accelerating FCM neural network classifier using graphics processing units with CUDA
Applied Intelligence
| Hi-index | 0.00 |
In the paper the problem of using a differential evolution algorithm for feed-forward neural network training is considered. A new parallelization scheme for the computation of the fitness function is proposed. This scheme is based on data decomposition. Both the learning set and the population of the evolutionary algorithm are distributed among processors. The processors form a pipeline using the ring topology. In a single step each processor computes the local fitness of its current subpopulation while sending the previous subpopulation to the successor and receiving next subpopulation from the predecessor. Thus it is possible to overlap communication and computation using non-blocking MPI routines. Our approach was applied to several classification and regression learning problems. The scalability of the algorithm was measured on a compute cluster consisting of sixteen two-processor servers connected by a fast Infiniband interconnect. The results of initial experiments show that for large datasets the algorithm is capable of obtaining very good, near linear speedup.