Dynamic neutral network model training method based on ensemble learning and dynamic neutral network model training device thereof

Abstract

The invention discloses a training method and device for a dynamic neural network model based on integrated learning, the method comprising: for each sub-model in the integrated dynamic neural network model, the original data is used as the input of the first layer of neurons, after The processing of dynamic neurons obtains the output features of this layer; increases the number of neuron layers, uses the output features of the upper layer as the input of the next layer of neurons, and obtains the features of the corresponding layer, and repeats this step until the number of layers reaches a certain preset value ; Establish a fully connected layer between the output feature of the last layer and the category to which it belongs, and calculate the fully connected weight between the output feature and the category; establish a fully connected layer between each sub-model and the category to which it belongs, and determine each The weight of the sub-model for the integrated dynamic neural network model; the present invention converts a deep neural network into multiple relatively shallow neural networks for parallel processing, saving training time and improving training efficiency.

Description

technical field [0001] The invention relates to the fields of artificial intelligence and big data, in particular to a model training method and device for object classification. Background technique [0002] Artificial intelligence has become a research hotspot in the current society. From time to time, new research results will catch people's attention and become a hot favorite in today's society. Among them, the correct classification and identification of objects has become an important research direction of artificial intelligence. At present, object recognition has made considerable progress, largely due to artificial neural networks and their many variants, such as convolutional neural networks, recurrent neural networks, etc. The neural network trains its internal structure through a large amount of data to achieve a strong expression effect of the model. However, the increase in the amount of data further increases the difficulty of model training. In order to sol...

AI Technical Summary

Problems solved by technology

In this model, the depth of the model and the design of the convolution function and the pooling function are extremely complicated and difficult problems. In addition, the current neural network and its various variants all model neurons as static neurons. The element can only describe the relationship between the input and the output, but cannot effectively describe the relationship between the system inputs, and cannot guarantee the classification performance of the neural network.

Images