From the 1 of 3 linked papers with an AI index.
3 papers
cs.LG2026
Lag Operator SSMs: A Geometric Framework for Structured State Space Modeling
Sutashu Tomonaga, Kenji Doya, Noboru Murata
The paper proposes a geometric, first‑principles framework for building discrete‑time structured state space models using a novel lag operator, enabling modular design of sequence…
cs.LG2026
LIG: Layer-wise Integrated Gradients for Within-Layer Flow Analysis in Transformers
Eight Suzuki, Hideitsu Hino, Noboru Murata
Transformers achieve strong performance, but their internal computations remain opaque. We view each Transformer layer as a dynamic graph whose nodes are token representations and…
cs.LG2025
Neural Tangent Kernels and Fisher Information Matrices for Simple ReLU Networks with Random Hidden Weights
Jun'ichi Takeuchi, Yoshinari Takeishi, Noboru Murata +3
Fisher information matrices and neural tangent kernels (NTK) for 2-layer ReLU networks with random hidden weight are argued. We discuss the relation between both notions as a linea…