A Neural Network Model Optimization Method Based on Class Expansion Learning

Abstract

The invention discloses a neural network model optimization method based on class expansion learning. The specific steps are as follows: Obtain a data set containing samples of various categories for training, and define the algorithm goal; use a general model to extract the features of each type of picture in the data set, and evaluate the error-prone of each category according to the distribution of each type of feature Add the most error-prone types of data to the training pool, and use the data in the training pool to optimize the neural network; after the optimization is completed, add the remaining types of error-prone data to the training pool to expand the categories in the training pool , and use the training pool to further optimize the neural network on the basis of the neural network obtained in the previous training; continuously expand the training pool until the entire data set enters the training pool, and obtain the final optimized neural network model. The invention is applicable to the neural network model optimization based on multi-category data sets in supervised learning, and has better effect and robustness in the face of various complex situations.

Description

technical field [0001] The invention belongs to the field of computer vision, in particular to a neural network model optimization method based on class expansion learning. Background technique [0002] The optimization method of the neural network model is the underlying technology of artificial intelligence, and it is often used as the basis for high-level visual tasks, such as object detection, target recognition, semantic segmentation, etc. However, limited by computer computing resources and memory resources, current optimization methods for neural network models rely on batch stochastic gradient descent. This method is an iterative, batch-level learning model. Each training cannot use global data, but only one batch of data. Since the data for each training is usually distributed in an extremely sparse and scattered space, the optimization of the neural network model is very difficult, and it will be affected by most of the simple data while optimizing, ignoring the i...

AI Technical Summary

Problems solved by technology

However, this type of optimization method has many details, high implementation cost, and difficult to reproduce; on the other hand, this type of method often designs specific evaluation indicators for specific tasks, and its evaluation indicators do not have the ability to migrate

Images