INFERENCE METHOD, INFERENCE DEVICE AND TRAINING METHOD USING NEURAL NETWORK

To provide an inference method, an inference device and a training method using a neural network, which relatively reduce a load applied to a neural network in comparison to a case of restoring the entire training data, and further improve generalization in an important region of training data.SOLUT...

Full description

Saved in:
Bibliographic Details
Main Authors CHANG HYUN-SUNG, SON MINJUNG
Format Patent
LanguageEnglish
Japanese
Published 19.04.2022
Subjects
Online AccessGet full text

Cover

Loading…
More Information
Summary:To provide an inference method, an inference device and a training method using a neural network, which relatively reduce a load applied to a neural network in comparison to a case of restoring the entire training data, and further improve generalization in an important region of training data.SOLUTION: A method comprises receiving input data S210, and determining information inferred from input data based on state information that activates a neural network in response to the input data S220. An embedded vector, which is generated by encoding the input data with at least part of the neural network, contains information that restores a first subregion in the input data with a first accuracy and a second subregion in the input data with a second accuracy. The first subregion is adaptively determined corresponding to at least one of the inferred information and the state information.SELECTED DRAWING: Figure 2 【課題】トレーニングデータ全体を復元することに比べて、神経網に与えられる負荷を相対的に減少させる一方、トレーニングデータの重要領域における汎化性を向上させる神経網を用いた推論方法、推論装置及びトレーニング方法を提供する。【解決手段】方法は、入力データを受信しS210、入力データに反応して神経網が活性化する状態情報に基づいて、入力データから推論された情報推論された情報を決定するS220。神経網の少なくとも一部を用いて入力データを符号化することで、生成される埋め込みベクトルは、入力データ内の第1部分領域を第1正確度で復元し、入力データ内の第2部分領域を第2正確度で復元する情報を含む。第1部分領域は、推論された情報及び状態情報のうち少なくとも1つに対応して適応的に決定される。【選択図】図2
Bibliography:Application Number: JP20210101605