Search Results for author: Naoki Nishikawa

Found 2 papers, 0 papers with code

State Space Models are Comparable to Transformers in Estimating Functions with Dynamic Smoothness

no code implementations29 May 2024 Naoki Nishikawa, Taiji Suzuki

Deep neural networks based on state space models (SSMs) are attracting much attention in sequence modeling since their computational cost is significantly smaller than that of Transformers.

Adaptive Topological Feature via Persistent Homology: Filtration Learning for Point Clouds

no code implementations NeurIPS 2023 Naoki Nishikawa, Yuichi Ike, Kenji Yamanishi

Machine learning for point clouds has been attracting much attention, with many applications in various fields, such as shape recognition and material science.

Cannot find the paper you are looking for? You can Submit a new open access paper.