Dr Michael Garcia Ortiz • City, University of London

Contact details

Address

Dr Michael Garcia Ortiz A309F , College Building [A]
City, University of London
Northampton Square
London EC1V 0HB
United Kingdom

About
Publications

About

Overview

My main interest lies in Artificial General Intelligence and Robotics, and in particular the emergence of common-sense knowledge through sensorimotor prediction. Sensorimotor prediction is a very powerful drive, allowing an embodied agent to acquire knowledge and build a model about its world. I am particularly interested in end-to-end self-supervised learning approaches inspired from insights in Neuroscience and Cognitive Development. Recently, I have been working on topics involving agents navigating in a physical world and learning representations of spatial displacement, as well as learning the structure of their environment (emergence of object representation), guided solely by prediction on continuous sensorimotor streams.

List of topics of Interest:
- Artificial General Intelligence
- State Representation Learning
- Sensorimotor Prediction
- Continual Learning

I am a member of the Research Center on Artificial Intelligence CitAI:
CitAI

Employment

Lecturer, City, University London, Jul 2019 – present
Research Scientist, Softbank Robotics Europe, Sep 2013 – May 2019

Publications

Publications by category

Conference papers and proceedings (16)

Caselles-Dupre, H., Garcia-Ortiz, M. and Filliat, D. (2021). S-TRIGGER: Continual State Representation Learning via Self-Triggered Generative Replay. 2021 International Joint Conference on Neural Networks (IJCNN) 18-22 July.doi:10.1109/ijcnn52387.2021.9533683
Jankovics, V., Garcia Ortiz, M. and Alonso, E. (2021). HetSAGE: Heterogenous Graph Neural Network for Relational Learning. The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21), 35(18): 15803-4. 2-9 February.
Caselles-Dupré, H., Garcia-Ortiz, M. and Filliat, D. (2021). On the Sensory Commutativity of Action Sequences for Embodied Agents. 20th International Conference on Autonomous Agents and Multiagent Systems.
Caselles-Dupré, H., Garcia Ortiz, M. and Filliat, D. (2019). Symmetry-Based Disentangled Representation Learning requires Interaction
with Environments. Thirty-third Conference on Neural Information Processing Systems (NeurIPS 2019) 8-14 December, Vancouver, Canada.
Laflaquiere, A. and Garcia Ortiz, M. (2019). Unsupervised Emergence of Egocentric Spatial Structure from Sensorimotor Prediction. Thirty-third Conference on Neural Information Processing Systems 8-14 December, Vancouver.
Lesort, T., Caselles-Dupre, H., Garcia-Ortiz, M., Stoian, A. and Filliat, D. (2019). Generative Models from the perspective of Continual Learning. 2019 International Joint Conference on Neural Networks (IJCNN) 14-19 July. doi:10.1109/ijcnn.2019.8851986
Ortiz, M.G. and Laflaquiere, A. (2018). Learning Representations of Spatial Displacement through Sensorimotor Prediction. 2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) 17-20 September. doi:10.1109/devlrn.2018.8761034
Caselles-Dupré, H., Garcia Ortiz, M. and Filliat, D. (2018). Continual State Representation Learning for Reinforcement Learning using
Generative Replay. Workshop on Continual Learning, NeurIPS 2018- Thirty-second Conference on Neural Information Processing Systems.
Kulak, T. and Garcia Ortiz, M. (2018). Emergence of Sensory Representations Using Prediction in Partially Observable Environments. Artificial Neural Networks and Machine Learning - ICANN 2018.
Annabi, L. and Garcia Ortiz, M. (2018). State representation learning with recurrent capsule networks. Workshop on Modeling the Physical World: Perception, Learning, and Control, NeurIPS 2018 - Thirty-second Conference on Neural Information Processing Systems.
Caselles-Dupre, H., Annabi, L., Hagen, O., Garcia Ortiz, M. and Filliat, D. (2018). Flatland: a Lightweight First-Person 2-D Environment for Reinforcement Learning. Workshop on Continual Unsupervised Sensorimotor Learning - ICDL-Epirob 2018.
Garcia Ortiz, M. (2017). Sensorimotor Prediction with Neural Networks on Continuous Spaces. Artificial Neural Networks and Machine Learning – ICANN 2017. doi:10.1007/978-3-319-68600-4_10
Gepperth, A., Garcia Ortiz, M. and Heisele, B. (2013). Real-time pedestrian detection and pose classification on a GPU. 2013 16th International IEEE Conference on Intelligent Transportation Systems - (ITSC 2013) 6-9 October. doi:10.1109/itsc.2013.6728256
Garcia Ortiz, M., Kummert, F. and Schmudderich, J. (2012). Prediction of driver behavior on a limited sensory setting. 2012 15th International IEEE Conference on Intelligent Transportation Systems - (ITSC 2012) 16-19 September. doi:10.1109/itsc.2012.6338810
Garcia Ortiz, M., Fritsch, J., Kummert, F. and Gepperth, A. (2011). Behavior prediction at multiple time-scales in inner-city scenarios. 2011 IEEE Intelligent Vehicles Symposium (IV) 5-9 June. doi:10.1109/ivs.2011.5940524
Caselles-Dupré, H., Garcia Ortiz, M. and Filliat, D. S-TRIGGER: Continual State Representation Learning via Self-Triggered
Generative Replay. International Joint Conference on Neural Networks.

Journal articles (6)

Irfan, B., Ortiz, M.G., Lyubova, N. and Belpaeme, T. (2022). Multi-modal Open World User Identification. ACM Transactions on Human-Robot Interaction, 11(1), pp. 1–50. doi:10.1145/3477963.
[publisher’s website]
Laflaquière, A. and Ortiz, M.G. (2019). Unsupervised Emergence of Egocentric Spatial Structure from Sensorimotor
Prediction. .
Laflaquière, A., Hemion, N., Ortiz, M.G. and Baillie, J.-.C. (2018). Grounding Perception: A Developmental Approach to Sensorimotor
Contingencies. .
Laflaquière, A. and Ortiz, M.G. (2018). Unsupervised Emergence of Spatial Structure from Sensorimotor Prediction. .
Kulak, T. and Ortiz, M.G. (2018). Representation Learning in Partially Observable Environments using
Sensorimotor Prediction. .
Gepperth, A.R.T., Garcia Ortiz, M., Sattarov, E. and Heisele, B. (2016). Dynamic attention priors: a new and efficient concept for improving object detection. Neurocomputing, 197, pp. 14–28. doi:10.1016/j.neucom.2016.01.036.