Application Ant Colony Neural Network in Lithology Recognition and Prediction: Evidence from China

BP neural network has some shortcomings, such as low-precision solutions, slow search speed and easy convergence to the local minimum points. Ant colony algorithm(ACA) is a novel simulated evolutionary algorithm which accounts for rapid discovery of good solutions and easy to realize distributed computation. This paper establishes ant colony neural network model and applies in lithology recognition and prediction. The model combines ant colony system with BP neural network, and ACA is been put forward to optimize authority value and threshold value of BP nerve network. The result shows that this model has extensive mapping ability of neural network and rapid global convergence of ant system. In generally, this model has significant advantages inspect of fast convergence speed, good generalization ability and not easy to yield minimal local results.