Learning device, learning method, and program

Abstract

A learning device includes: a plurality of learning modules, each of which performs update learning to update a plurality of model parameters of a pattern learning model that learns a pattern using input data; model parameter sharing means for causing two or more learning modules from among the plurality of learning modules to share the model parameters; module creating means for creating a new learning module corresponding to new learning data for learning the pattern when the new learning data are supplied as the input data; similarity evaluation means for evaluating similarities among the learning modules after the update learning is performed over all the learning modules including the new learning module; and module integrating means for determining whether to integrate the learning modules on the basis of the similarities among the learning modules and integrating the learning modules.

Description

technical field [0001] The present invention relates to a learning device, a learning method and a program, and in particular to a learning device, a learning method and a program capable of obtaining a pattern learning model with scalability and generalization capabilities. Background technique [0002] The pattern learning model that learns patterns may be, for example, RNN (Recurrent Neural Network), RNNPB (Recurrent Neural Network with Parameter Bias), or the like. The learning schemes of these pattern learning models are classified into "local representation" schemes and "distributed representation" schemes. [0003] In the "local representation" scheme, a plurality of patterns are learned in each of a plurality of learning modules of the respective learning pattern learning models (model parameters of the updating pattern learning models). Therefore, a learning module stores a pattern. [0004] Furthermore, in the "distributed representation" scheme, multiple pattern...

AI Technical Summary

Problems solved by technology

[0008] However, in the "distributed representation" scheme, the pattern memory has low stability and thus no scalability

Images