Adaptive dynamic cooperative particle swarm optimization method for feed-forward network

Abstract

The invention discloses an adaptive dynamic cooperative particle swarm optimization method for a feed-forward network. The method comprises the following steps of (1) initializing particles, and initializing sub-populations; (2) recording extreme values (pi) of particle individuals, an extreme value (pn) of each sub-population and a global extreme value (pg); (3) sorting the sub-populations according to the goodness of the extreme value (pn) of each sub-population, and determining the number of cooperative particles of the sub-populations; (4) enabling the particles in the sub-populations to learn from the extreme values (pi) of the particles and the extreme values (pn) of the sub-populations; (5) randomly selecting the cooperative particles from other sub-populations, enabling the cooperative particles to learn from the extreme values (pi) of the cooperative particles and the extreme values (pn) of the sub-populations, and updating the extreme values of the cooperative particles and social extreme values of the sub-populations to which the cooperative particles belong at any time according to the goodness of the particles; (6) updating particle information in sequence according to the steps (4 and 5), and randomly selecting at most two particles from a worse sub-population to enable the particles to become members of a better sub-population; (7) meeting all stopping conditions, stopping calculation, and otherwise, carrying out the step (2) for next iteration. By virtue of the method, the learning capacity and identification capacity of a network can be improved.

Description

technical field [0001] The present invention belongs to the field of pattern classification. This paper designs a dynamic adaptive cooperative particle swarm algorithm to optimize the feed-forward network, which has a wide range of applications in the fields of face recognition, smiley face recognition, and gender recognition. Background technique [0002] With its self-learning, self-organization, fault-tolerant characteristics and the ability to simulate nonlinear relationships, neural networks are particularly suitable for solving pattern classification problems. Hornik demonstrated that a three-layer feed-forward neural network can model complex nonlinear relationships with arbitrary precision [Ref. 1]. The realization of the above-mentioned performance of the neural network depends on the sufficient training of the neural network structure and weights under the guidance of a good objective function, so as to realize the law of the entire population in a limited learnin...

AI Technical Summary

Problems solved by technology

The algorithm adopts this kind of objective function, which is easy to fall into local extremum, which leads to insufficient generalization ability of the network

Images