I’m an associate professor at the Technical University of Denmark (DTU) in the Machine Learning for Smart Mobility (MLSM) group, where I’m working on machine learning models for understanding urban mobility and the behaviour of crowds. Previously, I was a H.C. Ørsted / Marie-Skłodowska Curie Actions (COFUND) postdoctoral fellow, also at DTU, working on spatio-temporal models of mobility demand with emphasis on modelling uncertainty and the effect of special events. I hold a PhD from University of Coimbra (Portugal), during which I worked on probabilistic models for learning from crowdsourced data.

My research interests include:

• Machine Learning and Pattern Recognition
• Crowdsourcing and Learning from Crowds
• Probabilistic Graphical Models and Bayesian inference
• Intelligent Transportation Systems and Urban Mobility

E-mail: rodr [at] dtu.dk – Google Scholar – GitHub

Selected publications:

• • Gammelli, D. and Rodrigues, F.
    Recurrent Flow Networks: A Recurrent Latent Variable Model for Spatio-Temporal Density Modelling [PDF] [Code]
    arXiv preprint arXiv:2006.05256, 2020
  • Gammelli, D. and Rolsted, K. and Pacino, D. and Rodrigues, F.
    Generalized Multi-Output Gaussian Process Censored Regression [PDF] [Code]
    arXiv preprint arXiv:2009.04822, 2020
  • Rodrigues, F.
    Scaling Bayesian inference of mixed multinomial logit models to very large datasets [PDF] [Code]
    arXiv preprint arXiv:2004.05426, 2020
  • Rodrigues, F. and Pereira, F. C.
    Beyond expectation: Deep joint mean and quantile regression for spatio-temporal problems [PDF] [Code]
    in IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2020
  • Rodrigues, F. and Ortelli, N. and Bierlaire, M. and Pereira, F. C.
    Bayesian Automatic Relevance Determination for Utility Function Specification in Discrete Choice Models [PDF] [Code]
    arXiv preprint arXiv:1906.03855, 2019
  • Rodrigues, F. and Azevedo, C. L.
    Towards Robust Deep Reinforcement Learning for Traffic Signal Control: Demand Surges, Incidents and Sensor Failures [PDF] [Code]
    in IEEE Intelligent Transportation Systems Conference (ITSC), 2019
  • Rodrigues, F. and Pereira, F. C.
    Deep Learning from Crowds [PDF] [Code] [Data]
    in The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI), 2018 (oral)
  • Rodrigues, F. and Markou, I. and Pereira, F. C.
    Combining Time-Series and Textual Data for Taxi Demand Prediction in Event Areas: a Deep Learning Approach [PDF] [Code+Data]
    in Information Fusion, Elsevier, 2018
  • Rodrigues, F. and Pereira, F. C.
    Heteroscedastic Gaussian Processes for Uncertainty Modeling in Large-Scale Crowdsourced Traffic Data [PDF]
    in Transportation Research Part C, Elsevier, 2018
  • Rodrigues, F. and Henrickson, K. and Pereira, F. C.
    Multi-output Gaussian Processes for Crowdsourced Traffic Data Imputation [PDF] [Code]
    in IEEE Transactions on Intelligent Transportation Systems, 2018
  • Petersen, N. and Rodrigues, F. and Pereira, F. C.
    Multi-output Bus Travel Time Prediction with Convolutional LSTM Neural Network
    in Expert Systems with Applications, Elsevier, 2018
  • Rodrigues, F. and Lourenço, M. and Ribeiro, B. and Pereira, F. C.
    Learning Supervised Topic Models for Classification and Regression from Crowds [PDF] [Code] [Data]
    in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2017
  • Rodrigues, F. and Borysov, S. and Ribeiro, B. and Pereira, F. C.
    A Bayesian Additive Model for Understanding Public Transport Usage in Special Events [PDF] [Code]
    in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2016
  • Rodrigues, F. and Pereira, F.C. and Ribeiro, B.
    Gaussian Process Classification and Active Learning with Multiple Annotators [PDF] [Code] [Data]
    in International Conference on Machine Learning (ICML), 2014