Dynamic programming algorithms for RNA secondary structure prediction with pseudoknots
Discrete Applied Mathematics - Special volume on combinatorial molecular biology
Chaotic neural networks with reinforced self-feedbacks and its application to N-Queen problem
Mathematics and Computers in Simulation
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
RNA secondary structure prediction is a computationally feasible and broadly studied problem. It can be considered as the combinatorial optimization problem. In this paper, we propose an improved transiently chaotic neural network (TCNN) for RNA secondary structure prediction. In the improved model, a variable p(t) called the acceptance probability of chaos is introduced into the original TCNN model. Variable p(t) is used to decide if the chaos term will be calculated or not. With variable p(t), the network can be speeded up to converge to a fixed point with fewer iterations. The improved TCNN is analyzed theoretically and evaluated experimentally through predicting RNA secondary structure. The simulation results show that the improved transiently chaotic neural network can reach stable state with fewer steps than the original transiently chaotic neural network.