LAB LOGA page on LabLog, a review site (not the lab's official page)
Neural Sequence Modeling Lab
Machine-translated · View original
A lab that uses deep learning to read both earthquake records and human language as sequence data.
AboutAbout the lab
Earthquakes and language, both solved as sequence data.
The Neural Sequence Modeling Lab studies complex data such as earthquake records and human language as sequence modeling problems.
Using deep learning and sequence alignment methods, the lab treats everything from fault motion over several decades to the structure of language within the same framework.
By combining mathematical theory with data science based on high-performance computing, the lab aims to build next-generation AI mechanisms that can extract causal relationships and predict future states.
Students interested in machine learning, earth science, or computational linguistics are welcome, and can gain experience with the latest supercomputers, AI frameworks (PyTorch, Hugging Face), and open-source software development.
Key terms
- Sequence modeling
- A method of using machine learning to handle ordered series of data, such as earthquake records or text
- Transformer
- A deep learning model that uses a mechanism called self-attention to capture which parts of a sequence are related to each other
- Low-resource
- Describes a language for which little data is available for training machine translation
ResearchResearch themes
The lab handles data from two different fields, earthquakes and language, as sequences using deep learning. For both physical phenomena and language, it aims to build AI architectures that can extract causal relationships and predict future states.
*Illustrative imageSequence Modeling of Earthquake Data
The lab applies marked point processes, edit distance, and self-attention mechanisms to complex earthquake data. Currently it uses large-scale Transformers and manifold learning to map the spatiotemporal changes of faults around the world.
*Illustrative imageMachine Translation for Low-Resource Languages
Viewing language as sequences, the lab aims to go beyond the limits of relying on empirical rules of thumb in machine translation for languages with little training data. It developed a method called Cross-Lingual Token Alignment Distance (CLTAD), which guides multilingual transfer learning in Transformers.
MembersFaculty
- Project Assistant ProfessorJUNQUEIRA SALDANHA MATHEUS HENRIQUE
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 Neural Sequence Modeling Lab
Machine Learning and Language Understanding LabSchool of Informatics, College of Media Arts, Science and TechnologyMachine learning, data mining
Applied Mathematical Systems LabSchool of Informatics, College of Media Arts, Science and TechnologyControl design engine: technology and theory for freely mani…Computational Geometry and Graphics LabSchool of Informatics, College of Media Arts, Science and TechnologyResearch on computer graphics: computer graphics (CG), rende…
Image Science LabSchool of Informatics, College of Media Arts, Science and TechnologyImage and video media processing and medical imaging; medica…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: “Facebook Data Center Server Board” Intel Free Press / CC BY 2.0 (cropped)
- Sequence Modeling of Earthquake Data: “Aerial-SanAndreas-CarrizoPlain” John Wiley / CC BY 3.0 (cropped)
- Machine Translation for Low-Resource Languages: “DSCF0614 Multilingual direction sign, Hampton Court Station” Donnanz / CC BY-SA 4.0 (cropped)
- Related lab (Machine Learning and Language Understanding Lab): “Chess game Staunton No. 6” Wilfredor / CC0 (cropped)
- Related lab (Applied Mathematical Systems Lab): “Wind turbine in full 01” Lauri Veerde / CC BY-SA 4.0 (cropped)
- Related lab (Image Science Lab): “Craig Joint Theater Hospital receives exclusive new CT scanner 150724-F-QU482-016” Senior Airman Cierra Presentado / Public domain (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.