LAB LOGA page on LabLog, a review site (not the lab's official page)
Intelligent Systems Lab
Machine-translated · View original
A lab developing next-generation artificial intelligence that adapts to change and withstands attacks.
AboutAbout the lab
Next-generation AI that withstands change and attacks.
The Intelligent Systems Lab develops next-generation artificial intelligence with robustness and adaptability.
Today's state-of-the-art AI cannot play 9x9 Go even after learning 19x19 Go, and its image recognition can be fooled by changing just one pixel.
The lab therefore aims to improve robustness and adaptability by developing new mechanisms and paradigms of intelligence.
Lab members can use state-of-the-art CPU and GPU servers.
Key terms
- Robustness
- The property of maintaining performance despite noise, attacks, or changes in the environment
- Reinforcement learning
- A framework regarded as the most general paradigm of machine learning, in which a system learns how to act from experience
- Evolutionary computation
- A computational method that, by analogy with biological evolution, searches for good solutions while changing a model's structure and weights from generation to generation
ResearchResearch themes
The lab aims to develop next-generation artificial intelligence with robustness and adaptability. It studies new learning mechanisms using reinforcement learning and evolutionary computation, analyses that probe learning systems by attacking them, and new optimization methods.
*Illustrative imageClassifiers that adapt to changing situations
The lab studies NOTC, a method that unifies two paradigms of reinforcement learning. Self-Organizing Classifiers, the family NOTC belongs to, update their states automatically through experience and can adapt even when a problem changes, such as a maze whose shape changes.
*Illustrative imageNeural models that evolve their structure
The lab studies SUNA, which unifies the functions of most proposed neurons into a single Unified Neural Model through reinforcement learning based on evolutionary computation. It evolves its own structure and can learn non-Markov problems.
*Illustrative imageHacking artificial intelligence
By attacking learning systems, the lab investigates how they understand categories such as "horse" and "ship." Because changing just one pixel can change the classification, the lab showed that these systems cannot be said to understand intelligently.
*Illustrative imageSAN: simple yet strong multi-objective optimization
SAN is a very simple multi-objective optimization algorithm that outperformed all other algorithms on the most difficult multi-objective benchmarks. The lab's analysis attributes this to its use of independent subpopulations, which avoid competition within the population of candidate solutions.
MembersFaculty
The Intelligent Systems Lab consists of faculty members, research assistants, doctoral, master's, and undergraduate students, research students, and interns.
- Associate ProfessorDanilo Vasconcelos Vargas
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 Intelligent Systems Lab
Information Security & Multimedia Security LabFaculty of Engineering, Department of Electrical Engineering and Computer ScienceCybersecurity and network security: new technologies and par…
Machine Learning, Data Mining, and AI LabFaculty of Engineering, Department of Electrical Engineering and Computer ScienceSince its establishment in 1996, the Suzuki Laboratory has w…
Multi-Agent LabFaculty of Engineering, Department of Electrical Engineering and Computer ScienceResearch on multi-agent systems, i.e., systems comprising mu…
Image and Media Understanding LabFaculty of Engineering, Department of Electrical Engineering and Computer ScienceCyber-physical systems that create social value by integrati…The 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: “Automatix Kuka robot being integrated.agr” ArnoldReinhold / CC BY-SA 4.0 (cropped)
- Classifiers that adapt to changing situations: “Active Learning Algorithm Used To Train Majority of Text2Image Model” MrAlanKoh / CC BY 4.0 (cropped)
- Neural models that evolve their structure: “Artificial Neural Network with Chip” mikemacmarketing / original posted on flickr Liam Huang / clipped and posted on flickr / CC BY 2.0 (cropped)
- Hacking artificial intelligence: “Hacker111” Sebastiaan ter Burg / CC BY-SA 2.0 (cropped)
- SAN: simple yet strong multi-objective optimization: “A murmuration of Starlings near Leominster in February - geograph.org.uk - 3347674” Jeremy Bolwell / CC BY-SA 2.0 (cropped)
- Related lab (情報セキュリティー & マルチメディアセキュリティ研究室): “Firewall-X400” Cuda-mwolfe / CC BY-SA 4.0 (cropped)
- Related lab (機械学習・
データマイニング・AI研究室): “Korean Robot” ApexInfinity Games / CC0 (cropped) - Related lab (マルチエージェント研究室): “Roundabout interchange” Petar Milošević / CC BY-SA 4.0 (cropped)
- Related lab (イメージ・メディア理解研究室): “USB webcam for PC” WrS.tm.pl / CC0 (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.