Neural network structure searching method and system, storage medium and equipment

Abstract

The invention relates to a neural network structure searching method and system, a storage medium and equipment, and the method comprises the steps: S1, obtaining a preset neural network architectureand a sampling structure; wherein the neural network architecture comprises an input layer, an output layer and a plurality of intermediate layers which are arranged in sequence; S2, according to thenetwork structure to be determined in each intermediate layer and the corresponding structure search interval, sampling for multiple times through a sampling structure, and obtaining a plurality of sub-neural-network structures; S3, performing classification training on the plurality of sub-neural-network structures to obtain a plurality of updated sub-neural-network structures and updated structure search intervals of the intermediate layers; s4, obtaining the classification accuracy of the updated plurality of sub-neural network structures, and updating the parameters of the sampling structure according to the accuracy; and S5, determining a required neural network structure. According to the method, the neural network structure with the effect most matched with the classification task can be automatically searched, time is saved, and efficiency is improved.

Description

technical field [0001] The invention relates to the field of signal processing, in particular to a search method, system, storage medium and equipment for a neural network structure. Background technique [0002] For the classification of signal data, the main methods are traditional machine learning methods and deep learning methods. The former is to artificially extract some features of the signal data, and then input the features into various classifiers to learn, and finally use the learned classifier to classify; the latter uses a deep neural network to simultaneously learn the features of the signal and perform Classification. In today's big data era, deep learning methods can learn richer and more useful features from big data. Therefore, deep learning methods are more and more widely used under big data. [0003] The core of the deep learning method lies in the structure of the neural network, and the neural network mainly includes a convolutional neural network; t...

AI Technical Summary

Problems solved by technology

Therefore, when designing a convolutional neural network structure for signal classification tasks, the designer needs to have certain experience in neural network structure design and parameter adjustment, and needs to keep trying to fine-tune it. The entire design process is complex and energy-consuming.

Images