CondenseNet algorithm fused with attention selection mechanism

Abstract

The invention provides a ContenseNet algorithm fused with an attention selection mechanism, and the algorithm comprises the steps: carrying out the feature extraction on data in a convolutional neuralnetwork through m network structure blocks, wherein each structure block comprises n groups of complete feature transformation layers, enabling the data to obtain a corresponding feature matrix through each feature transformation layer, cascading the m network structure blocks, performing feature extraction on data of the network structure blocks to obtain a final feature matrix, calculating a loss value of network training according to the obtained feature matrix, calculating an error term and a weight gradient of each layer, and judging whether the network is converged or not according to the loss value, if not, adjusting the convolutional neural network initialization parameter according to the weight gradient to perform training again, and if so, outputting a network training result.According to the CondenseNet algorithm fused with the attention selection mechanism, multi-dimensional feature information is efficiently utilized, the learning and expression capacity of a deep network is enhanced, and the classification accuracy is improved.

Description

technical field [0001] The invention belongs to the technical field of deep learning and big data, and in particular relates to a CondenseNet algorithm fused with an attention selection mechanism. Background technique [0002] In the face of massive, high-dimensional large sample data, deep learning has become a hot problem-solving method in the fields of computer vision and natural language processing due to its strong advantages of speed, accuracy, and intelligence. In recent years, with the innovation of related technologies, in-depth The learning field has continuously made breakthroughs. Scholars have successively improved network performance by increasing network depth; optimizing network structure to improve network accuracy and network applicability, but the deep learning network built by the traditional convolutional neural network The increasing accuracy of the network will reach saturation or even decrease, and the phenomenon of gradient disappearance will become ...

AI Technical Summary

Problems solved by technology

However, a problem inevitably brought about by the densely connected layer connection method is the redundant connection of the network and a large amount of memory.

Images