ABSTRACT
Objective To reduce the execution time of neural network training. Methods Parallel particle swarm optimization algorithm based on master-slave model is proposed to train radial basis function neural networks, which is implemented on a cluster using MPI libraries for inter-process communication. Results High speed-up factor is achieved and execution time is reduced greatly. On the other hand, the resulting neural network has good classification accuracy not only on training sets but also on test sets. Conclusion Since the fitness evaluation is intensive, parallel particle swarm optimization shows great advantages to speed up neural network training.
ABSTRACT
DNA computer is a new research field which combines bot h the computer science and molecular biology. DNA computer is proposed to solve a class of hard problems of mathematical complexity by using a set of DNA sequen ces encoding all candidate solutions to the computational problem of interest an d find out the correct answers by serial manipulations of biochemical reactions. DNA computer is exactly a biomolecular computer which stores a vast quantity of information with high density. DNA computer, by means of its huge parallel comp utation and brute force search strategy, can solve the NP complete problems with polynomial time. The recent advances and principle of DNA computer are introduc ed. The future development and the bioinformatical significance of DNA computer are also analyzed and discussed.