• Corpus ID: 233864463

KuraNet: Systems of Coupled Oscillators that Learn to Synchronize

@article{Ricci2021KuraNetSO,
  title={KuraNet: Systems of Coupled Oscillators that Learn to Synchronize},
  author={Matthew Ricci and Minju Jung and Yuwei Zhang and Mathieu Chalvidal and Aneri Soni and Thomas Serre},
  journal={ArXiv},
  year={2021},
  volume={abs/2105.02838}
}
Data Science Initiative, Brown University, Providence, RI 02906, USA Department of Cognitive, Linguistic and Psychological Sciences, Brown University, Providence, RI 02906, USA Department of Physics, Nankai University, Tianjin, China Artificial and Natural Intelligence Toulouse Institute, Université de Toulouse, Toulouse, France Department of Neuroscience, Brown University, Providence, RI 02906, USA Department of Computer Science, Brown University, Providence, RI 02906, USA 

Figures and Tables from this paper

Deep learning for bioimage analysis in developmental biology

How state-of-the-art methodologies have the potential to transform the understanding of biological systems through new image-based analysis and modelling that integrate multimodal inputs in space and time is analyzed.

Deep learning for bioimage analysis

How state-ofthe-art methodologies have the potential to transform the understanding of biological systems through new image-based analysis and modelling that integrate multimodal inputs in space and time is analysed.

References

SHOWING 1-10 OF 46 REFERENCES

Synchrony-optimized networks of non-identical Kuramoto oscillators

A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics

A database containing 'ground truth' segmentations produced by humans for images of a wide variety of natural scenes is presented and an error measure is defined which quantifies the consistency between segmentations of differing granularities.

Go with the flow: Adaptive control for Neural ODEs

A new module called neurally-controlled ODE (N-CODE) designed to improve the expressivity of NODEs, and is applied to an image Autoencoder endowed with a latent transformation flow, greatly improving representational power over a vanilla model and leading to state-of-the-art image reconstruction on CIFAR-10.

Opinion Dynamics on Discourse Sheaves

We introduce a novel class of Laplacians and diffusion dynamics on discourse sheaves as a model for network dynamics, with application to opinion dynamics on social networks. These sheaves are

Evolving flocking in embodied agents based on local and global application of Reynolds’ rules

This study study and demonstrate how evolutionary techniques can be used to synthesise flocking behaviours, in particular, how fitness functions should be designed to evolve high-performing controllers.

Efficient Graph Generation with Graph Recurrent Attention Networks

A new family of efficient and expressive deep generative models of graphs, called Graph Recurrent Attention Networks (GRANs), which better captures the auto-regressive conditioning between the already-generated and to-be-generated parts of the graph using Graph Neural Networks (GNNs) with attention.

Self-entrainment of a population of coupled non-linear oscillators

Data-driven discovery of coordinates and governing equations

A custom deep autoencoder network is designed to discover a coordinate transformation into a reduced space where the dynamics may be sparsely represented, and the governing equations and the associated coordinate system are simultaneously learned.

Earthquake sequencing: chimera states with Kuramoto model dynamics on directed graphs

It is surmised that one implication of the emergence of chimera states will lead to investigation of the present and other mathematical models in detail to generate global chimera-state maps similar to global seismicity maps for earthquake forecasting studies.

Neural Ordinary Differential Equations

This work shows how to scalably backpropagate through any ODE solver, without access to its internal operations, which allows end-to-end training of ODEs within larger models.