LAB LOGA page on LabLog, a review site (not the lab's official page)
Inoue Lab
Machine-translated · View original
A lab that integrates machine learning with knowledge representation and reasoning to build trustworthy AI.
AboutAbout the lab
Linking learning and reasoning toward trustworthy AI.
The Inoue Lab works to build explainable, robust AI by integrating machine learning and knowledge representation and reasoning, which have long been studied separately in AI research.
Going forward, the lab plans to also use the commonsense knowledge of large language models (LLMs) and apply it to advanced intellectual tasks.
The research is carried out at the National Institute of Informatics.
Students in the lab are given a seat at the National Institute of Informatics as collaborative graduate students, and can use the institute's computing environment and the generative AI models it develops.
Students can join this lab from the graduate level.
Key terms
- Symbolic reasoning
- Reasoning that derives logical conclusions from prior knowledge and assumptions expressed as logical formulas, in order to make correct decisions
- Neuro-symbolic AI
- AI that combines numerical computation by neural networks with symbolic reasoning
- Robustness
- Resistance to noise. Symbolic reasoning tends to lack it, and the lab says that integration with machine learning can compensate for this
ResearchResearch themes
Deep learning models and generative AI have reliability problems, such as unexpected behavior, misinformation, and bias. The Inoue Lab aims to build explainable, robust AI by integrating machine learning with symbolic systems that can handle goals, facts (knowledge), reasoning, and explanations.
Trustworthy, Explainable AI
To make AI more trustworthy, its interpretability, explainability, and robustness need to be improved. The lab continues its research with the aim of building explainable, robust AI by integrating machine learning with knowledge representation and reasoning.
Integrating Symbolic Reasoning and Machine Learning
Symbolic reasoning can explain and interpret its results, but it has difficulty acquiring knowledge and is weak against noise. To compensate for this through integration with machine learning, the lab works on the foundational technologies of neuro-symbolic AI and on reasoning capabilities for generative AI.
*Illustrative imageTrusted AI That Incorporates Constraints
The lab integrates machine learning with symbolic systems that can describe goals and facts as knowledge and constraints, and works on building machine learning models and generative AI systems that incorporate constraints. By combining neuro-symbolic AI, symbolic AI, and constraint processing, it aims to create a technical foundation for trusted AI.
MembersFaculty
- Affiliated ProfessorKatsumi Inoue
VoicesStudent voices
Ratings and reviews reflect the experiences of individual current or former students, not the lab's official views. Whether a lab has reviews, or how many, says nothing about the lab itself.
Students who take part in an interview may receive a thank-you gift worth ¥1,000, regardless of what they say.
Student ratings (0 students)
--
--
--
--
--
--
Student voices answer questions like these
- What's great about this lab?
- What did you learn after joining?
- What's the vibe, and what is the professor like?
- Who is this lab for?
- Where do graduates go?
Your experience can help younger students choose their lab. Your name won't be shown.
Write a lab reviewAnonymous · Your draft is saved if you stopRelatedLabs similar to Inoue Lab
Ito LabSchool of Informatics and Engineering, Class I (Informatics)Game informatics / artificial intelligence / cognitive scien…
Shibata LabSchool of Informatics and Engineering, Class I (Informatics)Kansei informatics, artificial intelligence, robotics, and h…
Sakamoto LabSchool of Informatics and Engineering, Class I (Informatics)Kansei AI, Kansei informatics, and sensory media
Ueno LabSchool of Informatics and Engineering, Class I (Informatics)Artificial intelligence / Machine learning / Data scienceThe information on this page is compiled by the LabLog team from the lab's public information and interviews. For corrections or removal requests, please contact LabLog, not the lab.
Report an errorAbout the images
The top and research theme images are illustrative and were not taken at the lab. They are cropped from Wikimedia Commons images. Cropped CC BY-SA images are provided under the same CC BY-SA license as the original (version shown on each line).
- Top image: “GEORGE BOOLE (Father of Symbolic Logic) REF-106865” William Murphy / CC BY-SA 2.0 (cropped)
- Trusted AI That Incorporates Constraints: “Wikimedia Foundation Servers-8055 08” Victorgrigas / CC BY-SA 3.0 (cropped)
- Related lab (伊藤 毅志 研究室): “Kyoto Shogi-initial position” Surligne / CC BY-SA 4.0 (cropped)
- Related lab (柴田 淳司 研究室): “Robots and Kids” Draganzivancevic / CC BY-SA 4.0 (cropped)
- Related lab (坂本 真樹 研究室): “Denim fabric 05 (Rico Cilliers and colormass via Poly Haven)” Rico Cilliers (Processing) colormass (Photography) / CC0 (cropped)
- Related lab (植野 真臣 研究室): “Bayesian network” Sachs K, Gifford D, Jaakkola T, Sorger P, Lauffenburger DA. / CC BY-SA 4.0 (cropped)
About LabLog
LabLog is a lab review app for students only. Student members at each university interview students in labs and publish what they say. Student voices can only be read by students who sign up with a university email address. Operated by bestiee Inc.
Learn more about LabLog ↗Search engines and AI may reference the basic lab info and rating summaries on this page and the description of LabLog. Student voices are for student members only. Automated collection by programs (scraping, or input to or training of AI) is prohibited under Article 8 of the Terms of Service. If you need data for research or analysis, please contact us.