Search Results for author: Naoya Takeishi

Found 13 papers, 4 papers with code

Asteroid Flyby Cycler Trajectory Design Using Deep Neural Networks

no code implementations23 Nov 2021 Naoya Ozaki, Kanta Yanagida, Takuya Chikazawa, Nishanth Pushparaj, Naoya Takeishi, Ryuki Hyodo

An asteroid flyby cycler trajectory design problem is a subclass of global trajectory optimization problems with multiple flybys, involving a trajectory optimization problem for a given flyby sequence and a combinatorial optimization problem to decide the sequence of the flybys.

Combinatorial Optimization

Learning interaction rules from multi-animal trajectories via augmented behavioral models

1 code implementation NeurIPS 2021 Keisuke Fujii, Naoya Takeishi, Kazushi Tsutsui, Emyo Fujioka, Nozomi Nishiumi, Ryoya Tanaka, Mika Fukushiro, Kaoru Ide, Hiroyoshi Kohno, Ken Yoda, Susumu Takahashi, Shizuko Hiryu, Yoshinobu Kawahara

In this paper, we propose a new framework for learning Granger causality from multi-animal trajectories via augmented theory-based behavioral models with interpretable data-driven models.

Time Series

Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling

no code implementations NeurIPS 2021 Naoya Takeishi, Alexandros Kalousis

A key technical challenge is to strike a balance between the incomplete physics and trainable components such as neural networks for ensuring that the physics part is used in a meaningful manner.

Discriminant Dynamic Mode Decomposition for Labeled Spatio-Temporal Data Collections

no code implementations19 Feb 2021 Naoya Takeishi, Keisuke Fujii, Koh Takeuchi, Yoshinobu Kawahara

Extracting coherent patterns is one of the standard approaches towards understanding spatio-temporal data.

Policy learning with partial observation and mechanical constraints for multi-person modeling

2 code implementations7 Jul 2020 Keisuke Fujii, Naoya Takeishi, Yoshinobu Kawahara, Kazuya Takeda

Extracting the rules of real-world biological multi-agent behaviors is a current challenge in various scientific and engineering fields.

Imitation Learning

Learning Dynamics Models with Stable Invariant Sets

no code implementations16 Jun 2020 Naoya Takeishi, Yoshinobu Kawahara

Invariance and stability are essential notions in dynamical systems study, and thus it is of great interest to learn a dynamics model with a stable invariant set.

On Anomaly Interpretation via Shapley Values

1 code implementation9 Apr 2020 Naoya Takeishi, Yoshinobu Kawahara

We focus on the semi-supervised anomaly detection and newly propose a characteristic function, on which the Shapley value is computed, specifically for anomaly scores.

Anomaly Detection Semi-supervised Anomaly Detection

Shapley Values of Reconstruction Errors of PCA for Explaining Anomaly Detection

no code implementations8 Sep 2019 Naoya Takeishi

We present a method to compute the Shapley values of reconstruction errors of principal component analysis (PCA), which is particularly useful in explaining the results of anomaly detection based on PCA.

Anomaly Detection

Physically-interpretable classification of biological network dynamics for complex collective motions

1 code implementation13 May 2019 Keisuke Fujii, Naoya Takeishi, Motokazu Hojo, Yuki Inaba, Yoshinobu Kawahara

A fundamental question addressed here pertains to the classification of collective motion network based on physically-interpretable dynamical properties.

General Classification

Knowledge-Based Regularization in Generative Modeling

no code implementations6 Feb 2019 Naoya Takeishi, Yoshinobu Kawahara

Prior domain knowledge can greatly help to learn generative models.

Knowledge-Based Distant Regularization in Learning Probabilistic Models

no code implementations29 Jun 2018 Naoya Takeishi, Kosuke Akimoto

Exploiting the appropriate inductive bias based on the knowledge of data is essential for achieving good performance in statistical machine learning.

Knowledge Graph Embeddings

Learning Koopman Invariant Subspaces for Dynamic Mode Decomposition

no code implementations NeurIPS 2017 Naoya Takeishi, Yoshinobu Kawahara, Takehisa Yairi

Spectral decomposition of the Koopman operator is attracting attention as a tool for the analysis of nonlinear dynamical systems.

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