MACHINE LEARNING APPARATUS, MACHINE LEARNING SYSTEM, MACHINE LEARNING METHOD, AND MACHINE LEARNING PROGRAM
To provide a machine learning apparatus using a convolutional neural network in consideration of security, and provide a machine learning system, a machine learning method, and a machine learning program.SOLUTION: A machine learning system is configured by connecting a machine learning apparatus to...
Gespeichert in:
1. Verfasser: | |
---|---|
Format: | Patent |
Sprache: | eng ; jpn |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | To provide a machine learning apparatus using a convolutional neural network in consideration of security, and provide a machine learning system, a machine learning method, and a machine learning program.SOLUTION: A machine learning system is configured by connecting a machine learning apparatus to a terminal device over a network so as to communicate with each other, the machine learning apparatus 100 including: a data acquisition unit 131 which acquires image data; and a machine learning calculation unit 132 which performs calculation processing using a convolutional neural network on the basis of the image data. The machine learning calculation unit includes: a cryptographic processing unit 1322 which executes arithmetic processing in a cryptography execution area using homomorphic encryption; a deciphering unit 1323 which executes arithmetic processing in a deciphering execution area; a shared memory to be accessed by the cryptographic processing unit and the deciphering unit; and a receiving unit 1321 which receives layer designation information to designate an N-th layer which is an intermediate layer between an input layer and an output layer of the convolutional neural network.SELECTED DRAWING: Figure 3
【課題】セキュリティを考慮した、畳み込みニューラルネットワークを用いた機械学習装置、機械学習システム、機械学習方法及び機械学習プログラムを提供する。【解決手段】機械学習装置と、端末装置とが、ネットワークを介して通信可能に接続される機械学習システムにおいて、機械学習装置100は、画像データを取得するデータ取得部131と、画像データに基づいて、畳み込みニューラルネットワークを用いた計算処理を行う機械学習計算部132と、を備える。機械学習計算部は、準同型暗号による暗号実行領域において演算する暗号処理部1322と、平文実行領域において演算する平文処理部1323と、暗号処理部及び平文処理部がアクセス可能な共有メモリと、畳み込みニューラルネットワークの入力層から出力層に向けての途中の層である第N層を指定する層指定情報を受け付ける受付部1321と、を有する。【選択図】図3 |
---|