Title:
INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD, AND INFORMATION PROCESSING PROGRAM
Document Type and Number:
WIPO Patent Application WO/2021/090897
Kind Code:
A1
Abstract:
An information processing device according to the present disclosure is provided with: an acquiring unit for acquiring a model having a neural network structure, and input information to be input into the model; and a generating unit for generating rationale information indicating a rationale relating to the output of the model after the input information has been input into the model, on the basis of state information indicating the state of the model after the input information has been input into the model.
Inventors:
SUZUKI KENJI (JP)
KOBAYASHI YOSHIYUKI (JP)
KOBAYASHI YOSHIYUKI (JP)
Application Number:
PCT/JP2020/041428
Publication Date:
May 14, 2021
Filing Date:
November 05, 2020
Export Citation:
Assignee:
SONY CORP (JP)
International Classes:
G08G1/16; G06N3/02
Domestic Patent References:
| WO2019087561A1 | 2019-05-09 |
Foreign References:
| JP2018154140A | 2018-10-04 | |||
| JP2019109675A | 2019-07-04 |
Other References:
MORI KEISUKE ET AL.: "Visual Explanation by Attention Branch Network for End-to-end Learning-based Self-driving", 2019 IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV, 9 June 2019 (2019-06-09), XP033606038
SELVARAJU RAMPRASAATH R. ET AL.: "Grad-CAM: Visual explanations from Deep Networks via Gradient-based Localization", 2017, pages 618 - 626, XP033282917, Retrieved from the Internet [retrieved on 20201202]
RIEGER LAURA ET AL.: "Aggregating explainability methods for neural networks stabilizes explanations", ARXIV.ORG, 1 March 2019 (2019-03-01), pages 1 - 10, XP081570146, Retrieved from the Internet [retrieved on 20201202]
KIM JINKYU ET AL.: "Interpretable Learning for Self-Driving Cars by Visualizing Causal Attention", IEEE, 2017, pages 2961 - 2969, XP033283163, Retrieved from the Internet [retrieved on 20201202]
See also references of EP 4057252A4
SELVARAJU RAMPRASAATH R. ET AL.: "Grad-CAM: Visual explanations from Deep Networks via Gradient-based Localization", 2017, pages 618 - 626, XP033282917, Retrieved from the Internet
RIEGER LAURA ET AL.: "Aggregating explainability methods for neural networks stabilizes explanations", ARXIV.ORG, 1 March 2019 (2019-03-01), pages 1 - 10, XP081570146, Retrieved from the Internet
KIM JINKYU ET AL.: "Interpretable Learning for Self-Driving Cars by Visualizing Causal Attention", IEEE, 2017, pages 2961 - 2969, XP033283163, Retrieved from the Internet
See also references of EP 4057252A4
Attorney, Agent or Firm:
SAKAI INTERNATIONAL PATENT OFFICE (JP)
Download PDF:
Previous Patent: ANTENNA AND WIRELESS COMMUNICATION DEVICE
Next Patent: METHOD FOR PRODUCING WATER-SOLUBLE POLYSACCHARIDES
Next Patent: METHOD FOR PRODUCING WATER-SOLUBLE POLYSACCHARIDES