LAB LOGA page on LabLog, a review site (not the lab's official page)
Shirakawa Lab
Machine-translated · View original
The lab researches artificial intelligence technologies such as evolutionary computation and machine learning.
AboutAbout the lab
Covering both fundamental algorithms and their application to real-world problems
The Shirakawa Lab conducts broad research and development on artificial intelligence technologies, including evolutionary computation, machine learning, and image processing and recognition.
The lab pursues both the development of fundamental algorithms and research that applies them to real-world problems.
It also carries out joint research with researchers within the university, at other universities, and at companies.
In addition to students of the Graduate School of Environment and Information Sciences, the lab accepts fourth-year students of the Computer Science Educational Program (EP) in the Faculty of Science and Engineering as graduation research students.
Key terms
- Machine learning
- A technology that builds models that make predictions and decisions based on data, and obtains useful knowledge and rules from that data.
- Black-box optimization
- An optimization approach that does not assume differentiability or convexity of the objective function, and therefore has a wide range of applications.
- Neural network architecture search
- A method for automatically searching for the architecture of a deep neural network, rather than designing it by hand.
NewsLab news
Paper by PhD students and others published in IEEE Access
Paper co-authored with the University of Tsukuba accepted at PPSN 2026
Paper by PhD students and others accepted at ICPR 2026
Paper by master's students and others accepted at GECCO 2026
Student selected as an Outstanding Student at Evostar 2026
ResearchResearch themes
The lab researches artificial intelligence technologies such as machine learning and evolutionary computation from two sides: developing fundamental algorithms and applying them to real-world problems. The themes below are examples, and students can work on any topic related to artificial intelligence, not only these.
*Illustrative imageNeural network architecture search
To get the most out of deep learning, an architecture suited to the data and the task must be designed, and trial and error by hand is unavoidable. The lab develops methods to search for such architectures automatically.
*Illustrative imageBlack-box optimization and evolutionary computation
Black-box optimization, which does not assume differentiability or convexity of the objective function, can be used for tasks such as hyperparameter optimization in machine learning. The lab works on improving the efficiency and the theoretical analysis of evolutionary computation algorithms.
*Illustrative imageResearch on large language models (LLMs)
The lab studies optimization related to large language models, such as prompt optimization and optimization of model merging, which combines multiple models. It also works on feature construction methods that use LLMs.
*Illustrative imageAutomatic gesture generation
Creating gestures for robots and anthropomorphic agents by hand places a heavy burden on developers. The lab generates them automatically from text and speech data using machine learning and deep learning.
MembersFaculty
The members of the Shirakawa Lab consist of faculty members, project faculty members, JSPS Research Fellows, administrative assistants, and doctoral, master's, and undergraduate students.As of 2026
- ProfessorShinichi Shirakawa
- Specially Appointed Faculty (Assistant Professor)Kento Uchida
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 Shirakawa Lab
Tanabe LabFaculty of Engineering Science, Department of Mathematics, Physics, Electrical Engineering and Computer ScienceFundamental research on evolutionary computation (black-box …
Fujimoto Lab (System Control Lab)Faculty of Engineering Science, Department of Mathematics, Physics, Electrical Engineering and Computer ScienceSystem optimization and automation, robotics, and actuators:…
Ichige Lab (Digital Sensing Lab)Faculty of Engineering Science, Department of Mathematics, Physics, Electrical Engineering and Computer ScienceDigital technology is involved in many aspects of our lives,…
Shikata LabFaculty of Engineering Science, Department of Mathematics, Physics, Electrical Engineering and Computer ScienceIn current and future information societies, computer techno…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: “UPS Power Management Module, racks with network cabling in NERSC data center” Derrick Coetzee from Berkeley, CA, USA / CC0 (cropped)
- Neural network architecture search: “Convolutional Neural Network” Irisbox / CC BY 4.0 (cropped)
- Black-box optimization and evolutionary computation: “Island model of the population of an evolutionary algorithm” Wilfried Jakob / CC BY-SA 4.0 (cropped)
- Research on large language models (LLMs): “Language model context understanding” Cepice / CC BY-SA 4.0 (cropped)
- Automatic gesture generation: “Tight gesture” Simon Villeneuve / CC BY-SA 4.0 (cropped)
- Related lab (Tanabe Lab): “Murmuration ( agrégation) d'un groupe d'étourneaux sur la sebkha de Sijoumi 3” Skander zarrad / CC BY-SA 4.0 (cropped)
- Related lab (Fujimoto Lab (System Control Lab)): “Sunderland University Experimental Robot Arm” MichaelShort1975 / CC BY-SA 4.0 (cropped)
- Related lab (Ichige Lab (Digital Sensing Lab)): “Digital Signal Processor 9997” Ashley Pomeroy / CC BY 3.0 (cropped)
- Related lab (Shikata Lab): “Asymmetric encryption scheme” MarcT0K (icons by JGraph) / CC BY 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.