Research field (2):
Neuroscience - general
, Biological, health, and medical informatics
Research keywords (3):
包括脳ネットワーク
, 非線形動力学
, 理論神経科学
Research theme for competitive and other funds (10):
2022 - 2025 Elucidation of regulatory mechanisms of reproductive division of labor in an ant using an automated behavior tracking system
2022 - 2024 Development of a new topological data analysis by integration with computational vison theory
2018 - 2023 背景脳活動が遍歴する下でも恒常的に感覚認識できる神経計算機構の解明
2016 - 2018 準素イデアル分解を用いた疎性へのアプローチ
2013 - 2017 Neural substrate of the internal model of the intention of others
2012 - 2016 statistical modeling of neural activities by infinite dimensional information geometry
2014 - 2016 Morse theoretic design of neuromorphic touch counters
2012 - 2014 Hodge分解によるヘテロ・大域的な脳活動の遍歴検出
2008 - 2012 Applications of Information Geometry to Computational Neuroscience
2006 - 2008 神経細胞が生成するスパイクの相関を利用した脳のモデル選択
Show all
Papers (53):
Ruriko Yoshida, Georgios Aliatimis, Keiji Miura. Tropical neural networks and its applications to classifying phylogenetic trees. IJCNN2024 (The International Joint Conference on Neural Networks). 2024
Masataka Konishi, Keiji Miura. Biologically plausible local synaptic learning rules implement CNNs and denoising autoencoders. International Conference on Scientific Computing and Machine Learning 2024 (SCML2024). 2024
David Barnhill, John Sabol, Ruriko Yoshida, Keiji Miura. Tropical Fermat-Weber Polytropes. 2024
Kurt Pasque, Christopher Teska, Ruriko Yoshida, Keiji Miura, Jefferson Huang. Tropical Decision Boundaries for Neural Networks Are Robust Against Adversarial Attacks. CoRR. 2024. abs/2402.00576
Ruriko Yoshida, David Barnhill, Keiji Miura, Daniel Howe. Tropical Density Estimation of Phylogenetic Trees. IEEE/ACM Transactions on Computational Biology and Bioinformatics. 2024. 1-9
Kazuki Nakada, Keiji Miura. Data Flow Representation of Machine Learning Algorithms and Hardware Accelerator Implementation. Note on Multiple-Valued Logic in Japan. 2018. 41. 12. 1-8
Kazuki Nakada, Keiji Miura, Makoto Kobayashi, Yasuyuki Murai, Iwao Sekita, Hisayuki Tatsumi. A Topology-based Feature Extraction and Its Application to Acoustic Digital Pen. Note on Multiple-Valued Logic in Japan. 2018. 41. 20. 1-8
Direct Feedback Alignment (DFA) Learning Rule can Implement Denoising Autoencoders in a Biologically Plausible Manner
(NEURO2024 2024)
Does the optimal structure of Vision Transformer (ViT) demonstrate a universal scaling law in accordance with the scale of the training data?
(NEURO2024 2024)
The comparison of the capacity of generating images of a diffusion model "DDIM" by replacing denoising CNNs
(NEURO2024 2024)
Tropical Neural Networks
(Mini-workshop on Geometry and Data Science at Naval Postgraduate School 2024)
Deep supervised learning can be realized robustly by layer-independent synaptic triad learning rule
(The 46th Annual Meeting of the Japan Neuroscience Society 2023)