Skip to content
Log in
Sponsored Design Multi-Agent AI Systems Using MCP and A2A: Engineer your own Pyt Design Multi-Agent AI Systems Using MCP and A2A: Engineer your own Pyt

Author

Ryota Shibusawa

View on Semantic Scholar

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#graph neural networks Open access Sep 2026

Approximate graph-fibration symmetry in connectome-constrained neural networks: code and results

Analysis and simulation code (loaders for the Janelia male CNS v1.0 and FlyWire v783 connectomes, an independent leaky integrate-and-fire implementation with Shiu et al. 2024 constants, mirror-symmetrisation and shuffle interventions, static mirror-defect analyses, quotient-network simulation, a teacher-student tying-granularity learning experiment) and all result files for the manuscript 'Approximate graph-fibration symmetry in connectome-constrained neural networks: cell-type quotients, equivariance, and behavioural bias'.

Ryota Shibusawa · 0 citations
#graph neural networks Open access Sep 2026

Approximate graph-fibration symmetry in connectome-constrained neural networks: code and results

Analysis and simulation code (loaders for the Janelia male CNS v1.0 and FlyWire v783 connectomes, an independent leaky integrate-and-fire implementation with Shiu et al. 2024 constants, mirror-symmetrisation and shuffle interventions, static mirror-defect analyses, quotient-network simulation, a teacher-student tying-granularity learning experiment) and all result files for the manuscript 'Approximate graph-fibration symmetry in connectome-constrained neural networks: cell-type quotients, equivariance, and behavioural bias'.

Ryota Shibusawa · 0 citations
#graph neural networks Open access Sep 2026

Approximate graph-fibration symmetry in connectome-constrained neural networks: code and results

Analysis and simulation code (loaders for the Janelia male CNS v1.0 and FlyWire v783 connectomes, an independent leaky integrate-and-fire implementation with Shiu et al. 2024 constants, mirror-symmetrisation and shuffle interventions, static mirror-defect analyses, quotient-network simulation, a teacher-student tying-granularity learning experiment) and all result files for the manuscript 'Approximate graph-fibration symmetry in connectome-constrained neural networks: cell-type quotients, equivariance, and behavioural bias'.

Ryota Shibusawa · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.