Day 1
Preliminary discussions & Registration
09:00 - 10:10
10:10 - 10:25
10:25 - 11:35
a Department of Computing and Mathematical Sciences, California Institute of Technology
b The Alan Turing Institute, London
Bridging Machine Learning, Dynamical Systems, and Algorithmic Information Theory: Insights from Sparse Kernel Flows, Poincaré Normal Forms and PDE Simplification
a Department of Computing and Mathematical Sciences, California Institute of Technology
Kernel Methods for the Approximation of the Eigenfunctions of the Koopman Operator
11:05 - 11:20 Matthieu Darcy a,(15min)
a Department of Computing and Mathematical Sciences, California Institute of Technology
Kernel Methods and Neural Networks for Solving Roughly Forced Partial Differential Equations
11:20 - 11:35 Matthew Levinea (15min)
a Eric and Wendy Schmidt Center, Broad Institute of MIT and Harvard
CD-Dynamax: fast and flexible Bayesian inference of dynamical systems from noisy, irregular, and partially-observed timeseries data
Lunch 11:35 - 13:30
13:30 - 14:50
a Faculty of Engineering, Shizuoka University
Kuramoto Reservoir Computing and Edge of Bifurcation
13:55 - 14:20 Thomas de Jonga (25min)
a Kanazawa University
Harnessing omnipresent oscillator networks as computational resource
14:20 - 14:35 Chun-Hsiung Hsia (15min)
aDepartment of Mathematics, National Taiwan University
Synchronization of Kuramoto oscillators with the time-delays and inertia effect
14:35 - 14:50 Ayumi Ozawaa (15min)
a Center for Mathematical Science and Advanced Technology, Japan Agency for Marine-Earth Science and Technology
Phase reduction of reaction-diffusion systems with discrete delay
Coffee break 14:50 - 15:10
15:10 - 16:40
a School of Mathematical Sciences, University College Cork
b INFANT Research Centre, University College Cork, Ireland.
Confabulation dynamics in a reservoir computer
15:35 - 16:00 Kazunori Matsuia (25min)
a Department of Logistics and Information Engineering, Tokyo University of Marine Science and Technology
Universal Approximation of ODENet and ResNet with a Single Composition of Affine and Activation Functions
16:00 - 16:25 Jeroen Lamba,b (25min)
a Department of Mathematics, Imperial College London
b International Research Center for Neurointelligence (IRCN), The University of Tokyo*
Equivariant learning through invariant theory
16:25 - 16:40 Tomohiro Taniguchia (15min)
a National Institute of Advanced Industrial Science and Technology
Physical reservoir computing by artificial spin ice
Coffee break 16:40 - 17:00
17:00 - 17:50
aDepartment of Electrical Engineering and Information Systems, The University of Tokyo
Generalizing hysteretic circuits to chaotic circuits as physical reservoir computers
17:25 - 17:50 Cristopher Salvia (25min)
a Department of Mathematics, Imperial College London
Parallelizing Transformers via Flow Discretization
Day 2
09:00 - 10:10
a Department of Mathematics and Statistics, Texas Tech University
Approximating dynamics as zero-noise limits
b Electrical Engineering Department, University of Washington
b AI Institute in Dynamic Systems, University of Washington
Deep Generative Modeling for Identification of Noisy, Non-Stationary Dynamical Systems
09:40 - 09:55 Yusuke Imotoa (15min)
a Institute for the Advanced Study of Human Biology, Kyoto University
RNA landscape in single cells
09:55 - 10:10 Takuma Sumia (15min)
a Advanced Institute for Materials Research (WPI-AIMR), Tohoku University
Numerical modeling of neuronal network recovery from injury using synaptic plasticity and modular organization
Coffee break 10:10 - 10:25
10:25 - 11:35
a NSF MSPRF Postdoctoral Fellow, Computing and Mathematical Sciences, California Institute of Technology
Microstructure-Dependent Differential Equations for Materials Simulation
10:50 - 11:05 Takashi Furuyaa (15min)
a Shimane University
Quantitative Approximation for Neural Operators in certain PDEs
11:05 - 11:20 Tomoyuki Kubotaa,b (15min)
a Graduate School of Information Science and Technology, The University of Tokyo
b Next Generation Artificial Intelligence Research Center (AI Center), The University of Tokyo
Introduction of Generalized Reservoir Computing
11:20 - 11:35 Keita Tokudaa (15min)
a Faculty of Health Data Science, Juntendo University
Low-Dimensional Transient Distribution of Ensemble Predictions of High-Dimensional Chaos and its Application to Control
Lunch 11:35 - 13:30
13:30 - 14:45
13:30 - 13:45 Nozomi Akashia (15min)
a Graduate School of Informatics, Kyoto University
Exploiting chaos in spin-torque oscillators for machine learning
13:45 - 14:00 Sora Todakaa (15min)
a Department of Informatics, Kyoto University
Exploiting dynamic programming algorithm of subset sum problem as a reservoir
14:00 - 14:15 Tempei Kabayamaa (15min)
a Graduate School of Information Science and Technology, University of Tokyo
Designing Chaotic Attractors: A Semi-supervised Approach
14:15 - 14:30 Yongbo Zhanga (15min)
a Graduate School of Information Science and Technology, The University of Tokyo
Reservoir direct feedback alignment: deep learning by physical dynamics
14:30 - 14:45 JingChuan Guana (15min)
a Intelligent Systems and Informatics Laboratory, Graduate School of Information Science and Technology, The University of Tokyo
Effects of noise on memory in linear recurrent networks
15:30 - 17:00
Conference dinner 18:00 - 20:00
Day 3
09:00 - 10:15
a Graduate School of Environmental, Life, Natural Science and Technology, Okayama University
Data-driven modeling from biased small training data using periodic orbits
09:45 - 10:00 Satoru Tadokoroa (15min)
a Education and Research Center for Mathematical and Data Science, Hokkaido University
Trans-bifurcation prediction of dynamics by extreme learning machines with control inputs
10:00 - 10:15 Yuya Tokutaa (15min)
a Institute for the Advanced Study of Human Biology, Kyoto University Institute for Advanced Study
Cross-species transcriptome analysis using Gromov-Wasserstein optimal transport
Coffee break 10:15 - 10:30
10:30 - 11:40
a School of Physical and Mathematical Sciences, Nanyang Technological University
Infinite-dimensional next-generation reservoir computing
11:10 - 11:25 Yuichiro Terasakia (15min)
a Department of Mechano-Informatics, The University of Tokyo
Dynamical Systems Theory for Bifurcation Generation
11:25 - 11:40 James Louwa (15min)
a Division of Mathematical Sciences, School of Physical and Mathematical Sciences, Nanyang Technological University
Prediction of causal dynamics using universal reservoirs
Lunch 11:40 - 13:30
13:30 - 14:35
Coffee break 14:35 - 14:55
14:55 - 16:00
Coffee break 16:00 - 16:20
16:20 - 17:10
a Institute for Molecules and Materials, Radboud University, Nijmegen
Chemical reservoir computation in a self-organizing reaction network
17:10 - 17:20
Email contact: dedsconf25@gmail.com