Oizmi Lab, Graduate School of Arts and Sciences, the University of Tokyo, M2
AMI AC SHARKS, 800m runner
Soh Takahashi*, Sasaki Masaru*, Ken Takeda, Masafumi Oizumi (2026) "Investigating Fine-and Coarse-grained Structural Correspondences Between Deep Neural Networks and Human Object Image Similarity Judgments Using Unsupervised Alignment." Neural Networks, 195, 108222. [link]
Soh Takahashi*, Sasaki Masaru*, Ken Takeda, Masafumi Oizumi (2024). "Self-supervised learning facilitates neural representation structures that can be unsupervisedly aligned to human behaviors." in ICLR 2024 Workshop on Representational Alignment. (*equal contribution) [link]
E-mail: soht121[at]g.ecc.u-tokyo.ac.jp