Research on a New Convolutional Neural Network Model Combined with Random Edges Adding
This work addresses performance bottlenecks in convolutional neural networks for computer vision tasks, but it appears incremental as it builds on existing small world network concepts.
The researchers tackled the problem of improving accuracy and convergence speed in convolutional neural networks by proposing a random edge adding algorithm based on small world network ideas, which increased model recognition accuracy and training convergence speed on Fashion-MNIST and CIFAR-10 datasets with a probability p=0.1.
It is always a hot and difficult point to improve the accuracy of convolutional neural network model and speed up its convergence. Based on the idea of small world network, a random edge adding algorithm is proposed to improve the performance of convolutional neural network model. This algorithm takes the convolutional neural network model as a benchmark, and randomizes backwards and cross-layer connections with probability p to form a new convolutional neural network model. The proposed idea can optimize the cross layer connectivity by changing the topological structure of convolutional neural network, and provide a new idea for the improvement of the model. The simulation results based on Fashion-MINST and cifar10 data set show that the model recognition accuracy and training convergence speed are greatly improved by random edge adding reconstructed models with aprobability p = 0.1.