3 papers
cs.LG2026
Foundations of Equivariant Deep Learning: Unifying Graph and Sheaf Neural Networks
Yoshihiro Maruyama
Symmetry is everywhere in nature and society. Geometric deep learning builds architectures respecting group symmetries, whereas topological deep learning organizes computation thro…
q-bio.NC2026
Modeling the Disjunction Effect within Classical Probability: A New Decision Process Model and Comparison with Quantum-like Models
Ryo Nasu, Yoshihiro Maruyama
The disjunction effect in human decision making is often taken to show that the classical law of total probability is violated, motivating quantum-like models. We re-examine this c…
cs.LG2025
Categorical Equivariant Deep Learning: Category-Equivariant Neural Networks and Universal Approximation Theorems
Yoshihiro Maruyama
We develop a theory of category-equivariant neural networks (CENNs) that unifies group/groupoid-equivariant networks, poset/lattice-equivariant networks, graph and sheaf neural net…