Art

J-GLOBAL ID：202202277350466315   Reference number：22A0714433

Neural Network Consoleによる説明可能なAI

Author (4)： SUZUKI KENJI (ソニーグループ R&Dセ) ,  KOBAYASHI YOSHIYUKI (ソニーグループ R&Dセ) ,  OBUCHI YUKIO (ソニーグループ R&Dセ) ,  NARIHIRA TAKUYA (ソニーグループ R&Dセ)
Material： ViEWビジョン技術の実利用ワークショップ講演論文集(CD-ROM)  (ViEW講演論文集(CD-ROM))
Volume： 2021  Page： ROMBUNNO.IS2-06  Publication year： Nov. 26, 2021 
JST Material Number： L4705C  Document type： Proceedings
Article type： 短報  Country of issue： Japan (JPN)  Language： JAPANESE (JA)

Thesaurus term： *neural network (biomodel) ,  *artificial intelligence ,  parameter ,  variable ,  black box ,  automatic classification ,  visualization ,  explanatory parameter
Semi thesaurus term： *AI (artificial intelligence) ,  image classification ,  explanatory parameter

JST classification (2)： Neurocomputers  (JC06010Q) ,  Artificial intelligence  (JE08000Z)

Reference (11)：

• Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, Dhruv Batra. Grad-CAM: Visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE International conference on computer vision, pages 618-626, 2017.
• Marco Tulio Riberio, Sameer Singh, and Carlos Guestrin. ′′Why shoud I trust you?′′ Explaining the predictions of any classifier. Proceedings of the 22nd ACM SIGKDD International conference on knowledge discovery and data mining, pages 1135-1144, 2016.
• Scott M Lundberg and Su-In Lee. A Unified Approach to Interpreting Model Predictions. In Advances in Neural Information Processing Systems 30, pages 4768-4. 2017.
• Daniel Smilkov, Nikhil Thorat, Been Kim, Fernanda Viegas, and Martin Wattenberg. SmoothGrad: removing noise by adding noise. arXiv:1706.03825, 2017.
• Neural Network Console URL: https://dl.sony.com/ja/

Terms in the title (1)： 説明可能なAI