Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Ryan-Rhys Griffiths

Ryan-Rhys Griffiths

Extracting associations and meanings of objects depicted in artworks through bi-modal deep networks


Mar 16, 2022
Gregory Kell, Ryan-Rhys Griffiths, Anthony Bourached, David G. Stork

Figure 1 for Extracting associations and meanings of objects depicted in artworks through bi-modal deep networks
Figure 2 for Extracting associations and meanings of objects depicted in artworks through bi-modal deep networks
Figure 3 for Extracting associations and meanings of objects depicted in artworks through bi-modal deep networks
Figure 4 for Extracting associations and meanings of objects depicted in artworks through bi-modal deep networks
* Accepted at Computer Vision and Image Analysis of Art (CVAA) conference 2022 
  Access Paper or Ask Questions

Hierarchical Graph-Convolutional Variational AutoEncoding for Generative Modelling of Human Motion


Nov 29, 2021
Anthony Bourached, Robert Gray, Ryan-Rhys Griffiths, Ashwani Jha, Parashkev Nachev

Figure 1 for Hierarchical Graph-Convolutional Variational AutoEncoding for Generative Modelling of Human Motion
Figure 2 for Hierarchical Graph-Convolutional Variational AutoEncoding for Generative Modelling of Human Motion
Figure 3 for Hierarchical Graph-Convolutional Variational AutoEncoding for Generative Modelling of Human Motion
Figure 4 for Hierarchical Graph-Convolutional Variational AutoEncoding for Generative Modelling of Human Motion
* Under Review 
  Access Paper or Ask Questions

Data Considerations in Graph Representation Learning for Supply Chain Networks


Jul 22, 2021
Ajmal Aziz, Edward Elson Kosasih, Ryan-Rhys Griffiths, Alexandra Brintrup

Figure 1 for Data Considerations in Graph Representation Learning for Supply Chain Networks
Figure 2 for Data Considerations in Graph Representation Learning for Supply Chain Networks
Figure 3 for Data Considerations in Graph Representation Learning for Supply Chain Networks
Figure 4 for Data Considerations in Graph Representation Learning for Supply Chain Networks
* ICML 2021 Workshop on Machine Learning for Data 
  Access Paper or Ask Questions

High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learning


Jun 16, 2021
Antoine Grosnit, Rasul Tutunov, Alexandre Max Maraval, Ryan-Rhys Griffiths, Alexander I. Cowen-Rivers, Lin Yang, Lin Zhu, Wenlong Lyu, Zhitang Chen, Jun Wang, Jan Peters, Haitham Bou-Ammar

Figure 1 for High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learning
Figure 2 for High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learning
Figure 3 for High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learning
Figure 4 for High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learning

  Access Paper or Ask Questions

Dataset Bias in the Natural Sciences: A Case Study in Chemical Reaction Prediction and Synthesis Design


May 06, 2021
Ryan-Rhys Griffiths, Philippe Schwaller, Alpha A. Lee

Figure 1 for Dataset Bias in the Natural Sciences: A Case Study in Chemical Reaction Prediction and Synthesis Design
Figure 2 for Dataset Bias in the Natural Sciences: A Case Study in Chemical Reaction Prediction and Synthesis Design
Figure 3 for Dataset Bias in the Natural Sciences: A Case Study in Chemical Reaction Prediction and Synthesis Design
Figure 4 for Dataset Bias in the Natural Sciences: A Case Study in Chemical Reaction Prediction and Synthesis Design
* Presented at the 2018 NeurIPS Workshop on Machine Learning for Molecules and Materials 
  Access Paper or Ask Questions

Computational identification of significant actors in paintings through symbols and attributes


Feb 04, 2021
David G. Stork, Anthony Bourached, George H. Cann, Ryan-Rhys Griffiths

Figure 1 for Computational identification of significant actors in paintings through symbols and attributes
Figure 2 for Computational identification of significant actors in paintings through symbols and attributes
Figure 3 for Computational identification of significant actors in paintings through symbols and attributes
Figure 4 for Computational identification of significant actors in paintings through symbols and attributes
* Accepted as conference paper at Computer Vision and Art Analysis 2021 
  Access Paper or Ask Questions

Resolution enhancement in the recovery of underdrawings via style transfer by generative adversarial deep neural networks


Jan 30, 2021
George Cann, Anthony Bourached, Ryan-Rhys Griffiths, David Stork

Figure 1 for Resolution enhancement in the recovery of underdrawings via style transfer by generative adversarial deep neural networks
Figure 2 for Resolution enhancement in the recovery of underdrawings via style transfer by generative adversarial deep neural networks
Figure 3 for Resolution enhancement in the recovery of underdrawings via style transfer by generative adversarial deep neural networks
Figure 4 for Resolution enhancement in the recovery of underdrawings via style transfer by generative adversarial deep neural networks
* Accepted for Publication at Computer Vision and Art Analysis, IS&T, Springfield, VA, 2021 
  Access Paper or Ask Questions

Recovery of underdrawings and ghost-paintings via style transfer by deep convolutional neural networks: A digital tool for art scholars


Jan 04, 2021
Anthony Bourached, George Cann, Ryan-Rhys Griffiths, David G. Stork

Figure 1 for Recovery of underdrawings and ghost-paintings via style transfer by deep convolutional neural networks: A digital tool for art scholars
Figure 2 for Recovery of underdrawings and ghost-paintings via style transfer by deep convolutional neural networks: A digital tool for art scholars
Figure 3 for Recovery of underdrawings and ghost-paintings via style transfer by deep convolutional neural networks: A digital tool for art scholars
Figure 4 for Recovery of underdrawings and ghost-paintings via style transfer by deep convolutional neural networks: A digital tool for art scholars
* Accepted to Electronic Imaging 2021: Computer Vision and image Analysis of Art 
  Access Paper or Ask Questions

Are we Forgetting about Compositional Optimisers in Bayesian Optimisation?


Dec 17, 2020
Antoine Grosnit, Alexander I. Cowen-Rivers, Rasul Tutunov, Ryan-Rhys Griffiths, Jun Wang, Haitham Bou-Ammar

Figure 1 for Are we Forgetting about Compositional Optimisers in Bayesian Optimisation?
Figure 2 for Are we Forgetting about Compositional Optimisers in Bayesian Optimisation?
Figure 3 for Are we Forgetting about Compositional Optimisers in Bayesian Optimisation?
Figure 4 for Are we Forgetting about Compositional Optimisers in Bayesian Optimisation?

  Access Paper or Ask Questions

Gaussian Process Molecule Property Prediction with FlowMO


Oct 14, 2020
Henry B. Moss, Ryan-Rhys Griffiths

Figure 1 for Gaussian Process Molecule Property Prediction with FlowMO
Figure 2 for Gaussian Process Molecule Property Prediction with FlowMO

  Access Paper or Ask Questions

Generative Model-Enhanced Human Motion Prediction


Oct 05, 2020
Anthony Bourached, Ryan-Rhys Griffiths, Robert Gray, Ashwani Jha, Parashkev Nachev

Figure 1 for Generative Model-Enhanced Human Motion Prediction
Figure 2 for Generative Model-Enhanced Human Motion Prediction
Figure 3 for Generative Model-Enhanced Human Motion Prediction
Figure 4 for Generative Model-Enhanced Human Motion Prediction
* 8 pages + 5 pages supplementary materials, under review at ICLR 
  Access Paper or Ask Questions

Achieving Robustness to Aleatoric Uncertainty with Heteroscedastic Bayesian Optimisation


Oct 17, 2019
Ryan-Rhys Griffiths, Miguel Garcia-Ortegon, Alexander A. Aldrick, Alpha A. Lee

Figure 1 for Achieving Robustness to Aleatoric Uncertainty with Heteroscedastic Bayesian Optimisation
Figure 2 for Achieving Robustness to Aleatoric Uncertainty with Heteroscedastic Bayesian Optimisation
Figure 3 for Achieving Robustness to Aleatoric Uncertainty with Heteroscedastic Bayesian Optimisation
Figure 4 for Achieving Robustness to Aleatoric Uncertainty with Heteroscedastic Bayesian Optimisation
* Accepted to the 2019 NeurIPS Workshop on Safety and Robustness in Decision Making 
  Access Paper or Ask Questions

Adaptive Sensor Placement for Continuous Spaces


May 16, 2019
James A Grant, Alexis Boukouvalas, Ryan-Rhys Griffiths, David S Leslie, Sattar Vakili, Enrique Munoz de Cote

Figure 1 for Adaptive Sensor Placement for Continuous Spaces
Figure 2 for Adaptive Sensor Placement for Continuous Spaces
Figure 3 for Adaptive Sensor Placement for Continuous Spaces
Figure 4 for Adaptive Sensor Placement for Continuous Spaces
* 13 pages, accepted to ICML 2019 
  Access Paper or Ask Questions

Constrained Bayesian Optimization for Automatic Chemical Design


Jun 27, 2018
Ryan-Rhys Griffiths, José Miguel Hernández-Lobato

Figure 1 for Constrained Bayesian Optimization for Automatic Chemical Design
Figure 2 for Constrained Bayesian Optimization for Automatic Chemical Design
Figure 3 for Constrained Bayesian Optimization for Automatic Chemical Design
Figure 4 for Constrained Bayesian Optimization for Automatic Chemical Design
* Previous versions accepted to the NIPS 2017 Workshop on Bayesian Optimization (BayesOpt 2017) and the NIPS 2017 Workshop on Machine Learning for Molecules and Materials 
  Access Paper or Ask Questions