MODEL COMPRESSION DEVICE, LEARNING SYSTEM, MODEL COMPRESSION METHOD, AND PROGRAM RECORDING MEDIUM

摘要

To efficiently create a prediction model, the prediction time of which is shortened while adequate generalization performance for machine learning is ensured, the model compression device, and the like, is equipped with a compression unit that creates a compression model arrived at by compressing a first prediction model created by machine learning, and a determination unit that determines whether or not a second prediction model created by re-learning the compression model can be further compressed on the basis of an index related to the performance of the second prediction model.