APSO-based Optimization Algorithm of LSTM Neural Network Model

For the multi hidden layer LSTM recurrent neural network, the updating of its weights and thresholds depends on the gradient descent algorithm, the convergence speed of the model is slow, and the weight calculation of the network nodes is prone to local extremum, which leads to the global optimization of the LSTM neural network model and the decline of the generalization ability of the network model, which limits the application of LSTM recurrent neural network. Therefore, this paper proposes an improved LSTM neural network model based on APSO algorithm. In this model, the root mean square error is designed as an appropriate value function, and the APSO algorithm is used to construct an optimization strategy to globally optimize the weights of each neuron node, so as to improve the generalization and prediction performance of the model. The experimental results of classic data market and UCI data sets show that the prediction accuracy of APSO-LSTM model is significantly improved compared with the traditional LSTM model, which verifies the effectiveness and practicability of APSO-LSTM model.