AM-RP Stacking PILers: Random projection stacking pseudoinverse learning algorithm based on attention mechanism

The stacking pseudoinverse learning algorithm can effectively improve the classification accuracy of the model and reduce the training time. However, the effect of random projection blocks on the neural network is often ignored, which reduces the performance of stacked generalization. To improve the generalization performance of neural networks and obtain high-quality classification results, we propose a random projection stacking pseudoinverse learning algorithm based on attention mechanism named AM-RP stacking PILers. Firstly, the input weight matrices with specific distributions are randomly generated, and then different random projection blocks are obtained through a pseudoinverse learning algorithm. Secondly, the training results of different random projection blocks are taken as a new input dataset, and the idea of attention mechanism is introduced to assign different weights to different random projection blocks. Finally, we use the stacking pseudoinverse learning algorithm to train a single hidden layer neural network and obtain the classification results with high generalization performance. The experimental results on a total of 76788 images in three public datasets of Salinas, MNIST and COIL-20 show that our algorithm achieves better performance in accuracy, precision, recall, F1 score and training time.