LAB LOGA page on LabLog, a review site (not the lab's official page)
Furuzuki Lab
Machine-translated · View original
A lab applying computational intelligence inspired by the brain and evolution to prediction and optimization.
AboutAbout the lab
Computation learned from living things, to predict and discriminate.
The Furuzuki Lab studies computational intelligence, which imitates the mechanisms of living things, and its applications.
It works with neural networks, fuzzy systems, genetic algorithms, and more, and in recent years has put particular effort into deep learning.
Its central interest is how to apply these techniques to tasks such as prediction, classification, clustering, and optimization.
Applications are wide-ranging, including pattern recognition, system identification and control, data mining, and financial analysis.
Key terms
- Computational intelligence
- A general term for techniques that imitate the mechanisms of living things, such as neural networks, fuzzy systems, and genetic algorithms
- Genetic algorithm
- A computational method that imitates biological evolution, searching for good solutions by selecting and recombining candidates
- System identification
- Building a mathematical model that describes the behavior of a target system from observed data
ResearchResearch themes
The Furuzuki Lab studies computational intelligence techniques such as neural networks, fuzzy systems, and genetic algorithms from an application standpoint. It aims to create new methods suited to each target field, based on information extracted automatically from that field.
*Illustrative imageQuasi-linear ARX neural networks
This is a model that represents a nonlinear system as a black box. Because it can also be identified in a form that is linear in the input, it can be designed in the same way as a linear controller. The lab studies modeling, parameter estimation, and control system design.
*Illustrative imageClassification with quasi-linear SVMs
This is a classifier that uses a kernel adapted to the data. It is built in two stages: first, local linear models are connected to roughly approximate the decision boundary, and then this rough model is optimized within the SVM framework.
*Illustrative imageHuman keypoint detection
This research aims to find the positions of all visible skeletal points, such as human joints, from a single image. It requires dense prediction that makes a decision for every pixel, and the lab is developing neural network architectures suited to this task.
MembersFaculty
- ProfessorTakayuki Furuzuki
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 Furuzuki Lab
Matsumaru LabGraduate School of Information, Production and Systems, Information Architecture FieldRobotics, mechatronics, human-robot interaction, personal ro…
Yoshie LabGraduate School of Information, Production and Systems, Information Architecture FieldVirtual communities, agents, multi-party interaction, e-main…
Fujimura LabGraduate School of Information, Production and Systems, Information Architecture FieldProduction planning, scheduling, next-generation production …
Ieiri LabGraduate School of Information, Production and Systems, Information Architecture FieldSocial informatics, human-computer interaction, agent-based …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: “Deep-dream-white-noise-0036” MartinThoma / CC0 (cropped)
- Quasi-linear ARX neural networks: “HUUSYA” C1815 / Public domain (cropped)
- Classification with quasi-linear SVMs: “MnistExamples” Josef Steppan / CC BY-SA 4.0 (cropped)
- Human keypoint detection: “2010 Motion Capture Suit” Mbrickn / CC0 (cropped)
- Related lab (松丸研究室): “Robonaut 2 on Centaur 2” NASA / Public domain (cropped)
- Related lab (吉江研究室): “Crane at construction site - geograph.org.uk - 7593527” Kevin Waterhouse / CC BY-SA 2.0 (cropped)
- Related lab (藤村研究室): “001 Car factory assembly line - Opel factory in Gliwice, Poland” Marek Ślusarczyk (Tupungato) Photo portfolio / CC BY 3.0 (cropped)
- Related lab (家入研究室): “Design Thinking Workshop WMDE 2” Corinna Schuster (WMDE) / 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.