Neural network model training method and device for weak annotation data

Abstract

The invention relates to a neural network model training method and device for weak labeled data. The method comprises the following steps: 1) learning tag prediction from input features through a feature flow deep neural network, and outputting a prediction result of a target tag; 2) learning tag prediction from the input multi-view weak tags through a tag flow deep neural network, and outputtinga prediction result of a target tag; and 3) using generalized cross entropy loss to define the consistency of the tags, and optimizing the prediction result of the target tag by jointly training thefeature flow deep neural network and the tag flow deep neural network. According to the method, feature and tag two-way learning tag prediction is adopted, models and knowledge are fused in a unifiedmode through double-flow collaboration, weak features and weak tags are considered at the same time, a model collaborative optimization strategy is innovatively constructed, and model optimization isguided through knowledge cross validation of the model and the weak features.

Description

technical field [0001] The invention belongs to the field of the Internet, and in particular relates to a neural network model training method and device based on weakly supervised learning. Background technique [0002] In recent years, artificial neural networks have made great achievements in the fields of machine learning and pattern recognition. The calculation model of artificial neural network is inspired by the central nervous system of animals, usually presented as interconnected "neurons", which can be estimated depending on a large number of inputs and general unknown approximate functions, and has a strong nonlinear relationship fitting ability . [0003] For example, a neural network for handwriting recognition is defined by a set of input neurons that are likely to be activated by pixels of an input image. After being weighted and transformed by a function (determined by the designer of the network), the actuations of these neurons are recognized by other neu...

AI Technical Summary

Problems solved by technology

[0010] The invention provides a neural network model training method and device for weakly labeled data to solve the technical problem of training a classification network with strong decision-making ability under the condition of inaccurate labels

Images