What's New
Our preprint has been posted on arXiv. Compositionality-Aware Graph2Seq Learning Takeshi D. Itoh, Takatomi Kubo, Kazushi Ikeda https://arxiv.org/abs/2201.12178Takatomi Kubo was appointed as associate professor of mathmetical informatics lab, NAIST, from Jan. 1st, 2022. https://isw3.naist.jp/Contents/Research/ai-04-en.htmlJanuary 30, 2020Our preprint has been posted on bioRxiv. https://biorxiv.org/cgi/content/short/2020.01.28.923953v1Overview of the Project
Our projects aim to unveil the cognitive processes in program comprehension as the unique higher cognitive function.
It is mainly consisted of three approaches: brain activity analysis, gaze behavior analysis, and modeling.
As the new projects, we are introducing other modalities, including ECG (not EEG).
Please stay tuned!!
Brain Activity Analysis
We are aiming to unveil the mechanism of neural processing during program comprehension with an fMRI scanner.
Modeling Approach
We are modeling the process of program comprehension.
Currently, we are using existing attention models for source code like code2vec, etc.
We will evaluate the validity of models through comparison with the gaze behavior of human subjects.Gaze Behavior Analysis
We are conducting experiments with an eye tracker to elucidate attended components in source code.
Members
Takatomi Kubo
Unit leader
Yoshiharu Ikutani
brain activity analysis (brain decoding)
machine learning for codes (graph representation learning),
contrasting gaze behavior and
attention models
Kiyoka Ikeda
gaze behavior analysis, contrasting gaze behavior and
attention models
Toyomi Ishida
TBA!
Hayato Tsubaki
machine learning (compositionality aware model)
Shahoor Kausmally
brain activity analysis
Yurina Wada
gaze behavior and/or ECG
Collaborators
TBA
Publication List
TBA
Outline of NAIST Summer School 2018
Staff member
- Takatomi Kubo
- (TA) Yoshiharu Ikutani
- (TA) Eri Nakahara
- Contents
Aug 6
- 9:20 - 10:00: Registration, etc.
- 10:00 - 10:50: Introduction (Kubo, Ikutani, Nakahara)
- Overview of general brain decoding
- Overview of brain decoding for code comprehension
- Preparation of materials (including installation of Matlab, SPM, and The Decoding Toolbox)
- 11:00 - 12:20: MRI and SPM (Kubo)
- (Functional) Neuroanatomy
- Principle of MRI measurement
- fMRI and SPM
- 13:30 - 14:50: Machine Learning (mainly SVM) (Kubo)
- 15:30 - 16:00: Brain decoding-1 Introduction (Ikutani)
- 16:00 - 17:00: Brain decoding-2 SPM Demo (Ikutani, Nakahara)
Aug 7
- 9:20 - 15:00: Brain decoding-3 Practice (Ikutani)
(10:30 - 10:40: short brak; 12:30 - 13:30: Lunch break) - 15:00 - 16:45: Brain decoding-4 Discussion (Ikutani)
Materials
0. Laptops will be prepared (except for the case you have Matlab in your system).
- fMRI Data (will be distributed)
- Matlab
- SPM
- The decoding toolbox
- MRIconvert
- Codes (will be distributed)
References
- Textbook
- MATLAB for Neuroscientists (Second Edition) https://www.sciencedirect.com/science/book/9780123838360#ancp4
- Statistical Parametric Mapping
https://www.elsevier.com/books/statistical-parametric-mapping-the-analysis-of-functional-brain-images/penny/978-0-12-372560-8
(PDF) http://www.fil.ion.ucl.ac.uk/spm/doc/books/hbf2/
- Web
- Matlab introduction https://jp.mathworks.com/help/pdf_doc/matlab/getstart_ja_JP.pdf
http://www.nemotos.net/resources/matlab_for_psychologists_ja.pdf
https://www.citl.titech.ac.jp/wp/wp-content/uploads/2015/07/seminar1129.pdf
http://www.slis.tsukuba.ac.jp/~hasegawa.hidehiko.ga/TUS/MATLAB.TUS.pdf - SPM http://www.fil.ion.ucl.ac.uk/spm/
- Neuroanatomy of the Brain http://www.neuroanatomy.ca/
© 2017