Laying the Foundation for Homomorphic Training of Neural Networks : An Analysis of the Required Computational Accuracy (BestMasters)

個数:
  • 予約

Laying the Foundation for Homomorphic Training of Neural Networks : An Analysis of the Required Computational Accuracy (BestMasters)

  • 現在予約受付中です。出版後の入荷・発送となります。
    (重要:表示されている発売日は予定となり、発売が延期、中止、生産限定品で商品確保ができないなどの理由により、ご注文をお取消しさせていただく場合がございます。予めご了承ください。)

    ●3Dセキュア導入とクレジットカードによるお支払いについて
  • 【入荷遅延について】
    世界情勢の影響により、海外からお取り寄せとなる洋書・洋古書の入荷が、表示している標準的な納期よりも遅延する場合がございます。
    おそれいりますが、あらかじめご了承くださいますようお願い申し上げます。
  • ◆画像の表紙や帯等は実物とは異なる場合があります。
  • ◆ウェブストアでの洋書販売価格は、弊社店舗等での販売価格とは異なります。
    また、洋書販売価格は、ご注文確定時点での日本円価格となります。
    ご注文確定後に、同じ洋書の販売価格が変動しても、それは反映されません。
  • 製本 Paperback:紙装版/ペーパーバック版/ページ数 306 p./サイズ 210mmx148mmx-
  • 言語 ENG
  • 商品コード 9783658529147

基本説明

This book investigates the impact of these approximations through a novel simulation framework. By evaluating various network architectures—including Multi-Layer Perceptrons and Convolutional Neural Networks—across multiple datasets, the author analyses the effects of Taylor series, Newton-Raphson, and Chebyshev polynomial approximations, alongside realistic Gaussian noise. The findings reveal that neural networks are inherently resilient to these errors, often maintaining or even improving baseline accuracy.

Full Description

As Artificial Intelligence becomes increasingly integrated into modern technology, the tension between data utility and individual privacy intensifies. Privacy-Preserving Machine Learning (PPML) addresses this conflict by utilizing techniques such as Homomorphic Encryption (HE), which enables computation on encrypted data. However, implementing HE in neural networks necessitates the use of functional approximations for complex non-linear operations, introducing errors that may affect model performance.

This book investigates the impact of these approximations through a novel simulation framework. By evaluating various network architectures—including Multi-Layer Perceptrons and Convolutional Neural Networks—across multiple datasets, the author analyses the effects of Taylor series, Newton-Raphson, and Chebyshev polynomial approximations, alongside realistic Gaussian noise. The findings reveal that neural networks are inherently resilient to these errors, often maintaining or even improving baseline accuracy. By establishing the necessary precision levels for common activation functions, this work demonstrates the feasibility of efficient homomorphic training, marking a vital advancement for secure and private machine learning.

最近チェックした商品