Research on Genetic Neural Network Algorithm and Its Application

Jing, Honglei; Xu, Xiang; Wang, Jinzhu

doi:10.1109/icvris.2018.00061

Cited by 3 publications

(2 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A genetic algorithm (GA) is a kind of evolutionary algorithm that works well in global optimization [28]. Compared with the BP neural network whose weights and biases are initialized randomly, the one whose weights and biases are initialized by GA (GA-BP) has a better approximation accuracy and fault tolerance ability [26]- [28]. However, it is uncommon in the literature to utilize GA-BP to train the model network.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Nearer Optimal and Faster Trained Value Iteration ADP for Discrete-Time Nonlinear Systems

Yang

Hou

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Adaptive dynamic programming (ADP) is generally implemented using three neural networks: model network, action network, and critic network. In the conventional works of the value iteration ADP, the model network is initialized randomly and trained by the backpropagation algorithm, whose results are easy to get trapped in a local minimum; both the critic network and action network are trained in each outer-loop, which is time-consuming. To approximate the optimal control policy more accurately and decrease the value iteration ADP training time, we propose a nearer optimal and faster trained value iteration ADP for discrete-time nonlinear systems in this study. First, before training the model network with a backpropagation algorithm, we use a global searching method, i.e., genetic algorithm, to evolve the weights and biases of the neural network for a few generations. Second, in the outer-loop training process, we propose a trigger mechanism to decide whether to train the action network or not, which can save much training time. Examples of both linear and nonlinear systems are induced to verify the superiority of the proposed method compared with the conventional value iteration ADP. The simulation results show that the proposed algorithm can provide a nearer optimal control policy and save more training time than the conventional value iteration ADP.INDEX TERMS ADP, value iteration, genetic algorithm, trigger mechanism.

show abstract

Section: Introductionmentioning

confidence: 99%

“…However, it is uncommon in the literature to utilize GA-BP to train the model network. Moreover, in the conventional GA-BP algorithm, GA often evolves BP neural network parameters for large numbers of generations, i.e., 500 generations in [26] and 1000 generations in [28], which is also time-consuming.…”

Section: Introductionmentioning

confidence: 99%