Friday Lunch Seminar: Kei Majima: ” Machine learning methods for brain decoding analysis ” (On-line & In-person for CiNet members only: Sign-up required)

Friday Lunch Seminar: Kei Majima: " Machine learning methods for brain decoding analysis " (On-line & In-person for CiNet members only: Sign-up required)

Friday Lunch Seminar (English)
June 30, 2023　　
12:15 〜 13:00
Conference Room, CiNet bldg. / On-line

Talk Title：Machine learning methods for brain decoding analysis

Kei Majima
Researcher
Institute for Quantum Life Science
National Institutes for Quantum Science and Technology

Abstract:
In this talk, I will introduce several machine learning methods we recently developed for decoding analysis: 1) a method for visualizing subjective images in the human mind based on brain activity [1], 2) a supervised algorithm designed for predicting discrete ordinal variables [2], and 3) a fast algorithm inspired by quantum computation, which approximates PCA and CCA and would allow for the analysis of huge-dimensional neural data [3]. Following these presentations, I would like to have discussions with CiNet members on possible collaborations.

[1] Koide-Majima, Nishimoto, Majima. Mental image reconstruction from human brain activity. bioRxiv preprint. 2023.
[2] Satake, Majima, Aoki, Kamitani. Sparse ordinal logistic regression and its application to brain decoding. Frontiers in Neuroinformatics. 2018.
[3] Koide-Majima, Majima. Quantum-inspired canonical correlation analysis for exponentially large dimensional data. Neural Networks. 2021.

Events archive