People
  1. Students
  2. Alumni
  3. Honorary Graduates
  4. Academic Experts
  1. Dr Eduardo Alonso
People

Contact Information

Contact

Visit Dr Eduardo Alonso

A304B, College Building

null

Postal Address

City, University of London
Northampton Square
London
EC1V 0HB
United Kingdom

About

Qualifications

BSc, MSc, PhD Philosophy, University of the Basque Country.

Employment

City University London, Reader in Computing.
Deputy Head of the Department of Computer Science.

RESEARCH INTERESTS

(1) Computational modelling and simulation in neuroscience and evolutionary biology.
(2) Data mining, analysis and visualisation of big data in health, transport, and financial applications.
(3) Control optimisation for smart grids and renewable energies.
(4) Deep Learning architectures and algorithms for cyber-security.
(5) Mathematical models of emergence and adaptation in Systems of Systems.

PhD STUDENTS WELCOME!

Please contact me if you are interested in doing a PhD in the areas above.
Requirements: Good programming skills (preferably but not limited to Java/C++; MATLAB; Python) and expertise in two of the following areas: neuroscience, machine learning, data science, control and optimisation, dynamic systems. Applicants would also need to have a strong mathematical background.

NEWS

(1) Awarded 1.9M EUR H2020 grant (H2020-EE-2015-2-RIA): Nicos Karcanias, George Halikias and Eduardo Alonso, for the project “Innovative Technology for District Heating and Cooling” (InDeal).

(2) Awarded £90K Baily Thomas Foundation grant to study "Learning in Autism: A systematic computational approach" with Sebastian Gaigg (SASS, City University London), Jennifer Cook (University of Birmingham), and Elliot Ludvig (University of Warwick).

(3) WINNER of the FIRST PRIZE of European Institute of Innovation and Technology (EIT) ICT Labs Idea Challenge on Smart Energy Systems in October 2014. Also winner of the UNIVERSITY RESEARCH COMPETITION PRIZE 2015, City University London.

(4) Our new Temporal Difference Learning model, Serial and Simultaneous Configural-cue Compound stimuli TD, has been published in PLoS ONE, 2014 (PLoS ONE 9(7): e102469. doi:10.1371/journal.pone.0102469). The simulator is available at http://www.cal-r.org/index.php?id=SSCC_TD_sim.

(5) Our work on "The Application of Temporal Difference Learning in Optimal Diet Models", (published in the Journal of Theoretical Biology) received the best talk award (4/800) at the 9th European Conference of Mathematical and Theoretical Biology, Gothenburg June 2014.

(6) "An Equivalence between Adaptive Dynamic Programming with a Critic and Backpropagation Through Time" has been spotlighted by the IEEE Computational Intelligence Society as one of the best eight papers in 2013.

Research

Control Optimisation in Energy

Industrial controllers for grid-connected converters (PI controllers in particular) are inherently limited due to their competing control nature. Practically, these limitations result in low power quality, inefficient power generation and transmission, and a possible loss of electricity, all of which cause loss of money for both electric utility companies and electric energy customers. This reduces system reliability and efficiency and affects the motivation for the customers to adopt energy generated from renewable resources. Our work is focused on developing adaptive control techniques for energy applications. More specifically, we have simulated a battery of neural network controllers trained with adaptive dynamic programming techniques which consistently outperform traditional PI controllers in that they are able to track reference currents under variable, switching conditions in real-time.

So far, we have prioritised the application of our technology to grid converters (HVDC and STATCOM) and have also carried out pilot experiments with PMS EDV motors. Our research may be instrumental in meeting DECC targets, and have a high impact in the adoption of affordable renewable energies and the development of smart grids. We are now engaged in the validation (hardware-in-the-loop testing) and commercialisation of our technology --and seeking to collaborate with companies in the energy sector. At the same time, we are expanding the application of our technology to ambient energy harvesting for wireless sensor networks.

In this and related research in optimal control I and Michael Fairbank's at City University London collaborate with Shuhui Li at The University of Alabama, Don Wunsch at the Missouri University of Science and Technology, and Danil Prokhorov, from Toyota Research Institute, Michigan.

Our research has resulted various patents and in high quality publications in IEEE Transactions in Neural Networks and Learning Systems, Neural Computation, Neural Networks, and in the Proceedings of the IEEE International Joint Conference on Neural Networks.

Computational Neuroscience

My work in computational neuroscience focuses on real-time error-correction models of associative learning. Together with Esther Mondragon at the Centre for Computational and Animal Learning Research (CAL), we have developed a representation of CSC Temporal Difference that extends the original model to incorporate stimulus configurations. This new model, called Serial and Simultaneous Configural-cue Compound stimuli TD (SSCC TD), offers a straightforward analysis of stimulus generalization and accounts for summation and context effects, non-linear discriminations, and, more significantly, structural discriminations, that is, discriminations that rely solely on the serial pattern of the stimulus arrangement. We are extending the model with attentional parameters now with Niklas Kokkola.

In addition, we are collaborating with Charlotte Bonardi (University of Nottimgham) and Domhnall Jennings (University of Newcastle), in their research on timing phenomena within an associative framework, and with Andre Luzardo, Francois Rivest (Royal Military College of Canada ), and Elliot Ludvig (University of Warwick) in adaptive drift-diffusion models of interval timing dynamics.

We believe it is paramount that computational models are implemented in simulators that quickly and accurately test their predictions. At CAL we develop cross-platform and user-friendly simulators of classical conditioning models for research and teaching purposes. In particular, with Jonathan Gray (University of Southampton) and Alberto Fernandez-Gil (Universidad Rey Juan Carlos), we have made available a Rescorla and Wagner's model simulator,CAL-RWSim, a CSC Temporal Difference simulator, CAL-TDSim, and a simulator of our SSCC TD model, SSCC-TDSim.

I also collaborate with Mark Broom and Jan Teichmann at the Centre of Mathematical Science in simulating how learning affects the evolution of aposematism and foraging, and with colleagues at the School of Arts and Social Sciences in applying computational models of learning to the study of eating disorders, and autism, and on the effects of social status on learning.

Finally, I help Nestor Schmajuk (Duke Institute for Brain Sciences) manage the Society for Computational Modeling of Associative Learning (SOCMAL).

Our research in this area has been published in PLoS ONE, the Journal of Experimental Psychology: Animal Behaviour Processes, Learning and Behavior, Neuroinformatics, Computer Methods and Programs in Biomedicine, the Journal of Theoretical Biology, and in the journal of Mathematical Modelling of Natural Phenomena.

Systems of Systems

Systems of Systems have been defined as systems that describe the large-scale integration of many independent self-contained systems to satisfy global needs or multi-system requests. They are characterized by their autonomy, emergence and adaptability. Notwithstanding their ubiquity and importance, we are still lacking appropriate tools and models for their design, implementation, and validation. With Nicos Karcanias (Systems and Control Centre) and Ali G. Hessami (Vega Systems), we are investigating at the City Complexity Science Group innovative ways to specify, develop, and analyze hierarchical Systems of Systems which combine physical and cyber structures.

We have presented preliminary results at the IEEE Systems Conference, and at the IEEE Conference on Systems, Man, and Cybernetics. In the practical side, we are interested in developing a Systems of Systems framework and architecture for the integration of smart technologies in safe and sustainable rail infrastructures –along with Bombardier plc.

Other research interests

I collaborate in projects involving multi-agent systems architectures, and communication and co-ordination protocols for health systems (personalized health systems, with Peter Weller at the Centre for Health Informatics, and the Universidad Rey Juan Carlos, Madrid) and telecommunication networks (with the Universidad Politecnica de Madrid), machine learning techniques for IT (cyber-security, with Kevin Jones at the Centre for Software Reliability), and data mining algorithms for safety in air transport (with UCL and easyJet plc).

Research Students

Name
Atif Riaz
Attendance
2015 – present
Thesis Title
Machine Learning for Functional Connectivity Analysis of Neurological Disorders Using Magnetic Resonance Imaging
Further Information
With Dr. Greg Slabaugh
Name
Andre Luzardo
Attendance
2014 – present
Thesis Title
A Model for Timing and Learning
Further Information
With Dr. Esther Mondragon
Name
Remilekun Basaru
Attendance
2013 – present
Thesis Title
Robust Hand-pose Recognition from Egocentric Stereovision
Further Information
With Dr. Greg Slabaugh and Dr. Chris Child
Name
Judit Guimera-Busquets
Attendance
2013 – present
Thesis Title
Applying Machine Learning Techniques to Analyse Operational Flight Data
Further Information
With Prof. Chris Atkin and Dr. Antony Evans
Name
Konstantin Pozdniakov
Attendance
2013 – present
Thesis Title
Unsupervised Machine Learning in Cyber-Security
Further Information
With Prof. Kevin Jones and Dr. Vladimir Stankovic
Name
Niklas Kokkola
Attendance
2013 – present
Thesis Title
Computational Models of Learning and Behaviour
Further Information
With Dr. Esther Mondragon
Name
Jan Teichmann
Attendance
2012 – 2015
Thesis Title
Modelling the Co-evolution of Defence and Signalling in Biological Populations with Aversive Learning
Further Information
With Prof. Mark Broom
Name
Michael Fairbank
Attendance
2011 – 2014
Thesis Title
Value-Gradient Learning
Name
Jonathan Turner
Attendance
2011 – present
Thesis Title
Modulation of Medical Condition Likelihood by Patient Similarity
Further Information
With Dr. Peter Weller, Dr. Peter Smith and Dr. Jonathan Bird
Name
Yousef Al-Mimi
Attendance
2010 – 2015
Thesis Title
The Routine Health Information System in Palestine: Determinants and Performance
Further Information
With Prof. Ewart Carson
Name
Reinhold Kloos
Attendance
2008 – 2014
Thesis Title
ACTAS: Adaptive Composition and Trading with Agents for Services
Further Information
With Prof. Michael Schroeder and Dr. Peter Smith
Name
Tshiamo Motshegwa
Attendance
2005 – 2009
Thesis Title
Distributed Termination Detection for Multiagent Protocols
Further Information
With Prof. Michael Schroeder
Name
Rodrigo Agerri
Attendance
2003 – 2006
Thesis Title
Motivational Attitudes and Norms in a unified Agent Communication Language for open Multi-Agent Systems: A Pragmatic Approach
Name
Penny Noy
Attendance
2001 – 2005
Thesis Title
Enhancing Comprehension of Complex Data Visualizations: Framework and Techniques Based on Signature Exploration
Further Information
With Prof. Michael Schroeder
Name
Marcus Pearce
Attendance
2001 – 2005
Thesis Title
Construction and Evaluation of Computational Models of Music Perception and Cognition
Further Information
With Prof. Geraint Wiggins
Name
Jack Gomoluch
Attendance
2001 – 2005
Thesis Title
Market-based Resource Allocation for Distributed Information Processing Applications
Further Information
With Prof. Michael Schroeder

Publications

Book (1)

  1. Alonso, E. and Mondragon, E. (2010). Computational Neuroscience for Advancing Artificial Intelligence: Models, Methods and Applications. Hershey, PA: IGI Global. ISBN 978-1-60960-021-1.

Chapter (4)

  1. Alonso, E. (2014). Actions and Agents. In Frankish, K. and Ramsey, W. (Eds.), The Cambridge Handbook of Artificial Intelligence (pp. 232–246). Cambridge, UK: Cambridge University Press. ISBN 978-0-521-87142-6.
  2. Fairbank, M., Prokhorov, D. and Alonso, E. (2013). Approximating Optimal Control with Value Gradient Learning. In Lewis, F. and Liu, D. (Eds.), Reinforcement Learning and Approximate Dynamic Programming for Feedback Control (pp. 142–161). Hoboken, NJ: Wiley-IEEE Press. ISBN 978-1-118-10420-0.
  3. Jennings, D.J., Alonso, E., Mondragón, E. and Bonardi, C. (2010). Temporal uncertainty during overshadowing: A temporal difference account. Computational Neuroscience for Advancing Artificial Intelligence: Models, Methods and Applications (pp. 46–55). ISBN 978-1-60960-021-1.
  4. Alonso, E. and Mondragón, E. (2010). Computational models of learning and beyond: Symmetries of associative learning. Computational Neuroscience for Advancing Artificial Intelligence: Models, Methods and Applications (pp. 316–332). ISBN 978-1-60960-021-1.

Conference Proceedings (23)

  1. Riaz, A., Alonso, E. and Slabaugh, G. (2016). Phenotypic Integrated Framework for Classification of ADHD using fMRI. Proc. of the International Conference on Image Analysis and Recognition (ICIAR 2016), 217-225 July, Póvoa de Varzim, Portugal.
  2. Busquets, J.G., Alonso, E. and Evans, A. (2016). Predicting Aggregate Air Itinerary Shares Using Discrete Choice Modeling. 16th AIAA Aviation Technology, Integration, and Operations Conference June, Washington, D.C.
  3. Basaru, R.R., Slabaugh, G., Child, C. and Alonso, E. (2016). HandyDepth: Example-based Stereoscopic Hand Depth Estimation using Eigen Leaf Node Features. Proceedings of the International Conference on Systems, Signals and Image Processing (IWSSIP 2016), 33-36 May, Bratislava, Slovakia.
  4. Shuhui, L., Fu, X., Jaithwa, I., Alonso, E., Fairbank, M. and Wunsch, D.C. (2015). Control of Three-Phase Grid-Connected Microgrids Using Artificial Neural Networks. Proceedings of the 7th International Joint Conference on Computational Intelligence (IJCCI 2015) - Volume 3: NCTA, 58-69 November, Lisbon, Portugal.
  5. Teichmann, J., Alonso, E. and Broom, M. (2015). A reward-driven model of Darwinian fitness. Proceedings of the 7th International Joint Conference on Computational Intelligence (IJCCI 2015) - Volume 1: ECTA, 174-179 November, Lisbon, Portugal.
  6. Li, S., Fu, X., Alonso, E., Fairbank, M. and Wunsch, D.C. (2016). Neural-network based vector control of VSC-HVDC transmission systems. Proceedings of the 4th International Conference on Renewable Energy Research and Applications (ICRERA), 173-180 Nov 2015, Palermo, Italy.
  7. Li, S., Alonso, E., Fu, X., Fairbank, M., Jaithwa, I. and Wunsch, D.C. (2015). Hardware Validation for Control of Three-Phase Grid-Connected Microgrids Using Artificial Neural Networks. 12th International Conference on Applied Computing, 3-10 October, Dublin, Ireland.
  8. Busquets, J.G., Alonso, E. and Evans, A. (2015). Application of Data Mining in Air Traffic Forecasting. 15th AIAA Aviation Technology, Integration, and Operations Conference, Vol.2, 783-798 October, Dallas, TX.
  9. Karcanias, N., Hessami, A.G. and Alonso, E. (2015). Complexity of Multi-Modal Transportation and Systems of Systems. Proceedings of the 47th Annual Universities’ Transport Study Group Conference (UTSG 2015) January, London, UK.
  10. Basaru, R.R., Child, C., Alonso, E. and Slabaugh, G. (2014). Quantized Census for Stereoscopic Image Matching. Second International Conference on 3D Vision (3DV 2014), 22-29 December, Tokyo, Japan.
  11. Alonso, E., Sahota, P. and Mondragon, E. (2014). Computational Models of Classical Conditioning: A Qualitative Evaluation and Comparison. Proceedings of the 6th International Conference on Agents and Artificial Intelligence (ICAART 2014), Vol. 1, pp. 2445-247 March, Angers, France.
  12. Alonso, E. and Mondragon, E. (2014). Quantum Probability and Operant Conditioning: Behavioral Uncertainty in Reinforcement Learning. Proceedings of the 6th International Conference on Agents and Artificial Intelligence (ICAART 2014), Vol. 1, pp. 2448-251 March, Angers, France.
  13. Weller, P., Fernandez, A. and Alonso, E. (2014). Towards a Personalised Health System. Proceedings of the 7th International Conference on Health Informatics (HEALTHINF 2014), pp. 256-261 March, Angers, France.
  14. Alonso, E. and Fairbank, M. (2013). Emergent and Adaptive Systems of Systems. IEEE International Conference on Systems, Man, and Cybernetics (IEEE SMC 2013), 1721-1725 October, Manchester, UK.
  15. Li, S., Fairbank, M., Fu, X., Wunsch, D. and Alonso, E. (2013). Nested-Loop Neural Network Vector Control of Permanent Magnet Synchronous Motors. IEEE International Joint Conference on Neural Networks (IEEE IJCNN 2013), 2999-3006 August, Dallas, TX.
  16. Alonso, E., Karcanias, N. and Hessami, A. (2013). Symmetries, groups and groupoids for Systems of Systems. IEEE International Systems Conference (SysCon 2013), 244-250 April, Orlando, FL.
  17. Alonso, E., Karcanias, N. and Hessami, A. (2013). Multi-Agent Systems: A new paradigm for Systems of Systems. Eighth International Conference on Systems (ICONS 2013), 8-12 January, Seville, Spain.
  18. Li, S., Fairbank, M., Wunsch, D. and Alonso, E. (2012). Vector Control of a Grid-Connected Rectifier/Inverter Using an Artificial Neural Network. IEEE International Joint Conference on Neural Networks (IEEE IJCNN 2012), 1783-1789 June, Brisbane, Australia.
  19. Fairbank, M. and Alonso, E. (2012). A Comparison of Learning Speed and Ability to Cope Without Exploration between DHP and TD(0). IEEE International Joint Conference on Neural Networks (IEEE IJCNN 2012), 1478-1485 June, Brisbane, Australia.
  20. Fairbank, M. and Alonso, E. (2012). Value-Gradient Learning. IEEE International Joint Conference on Neural Networks (IEEE IJCNN 2012), 3062-3069 June, Brisbane, Australia.
  21. Fairbank, M. and Alonso, E. (2012). The divergence of reinforcement learning algorithms with value-iteration and function approximation. IEEE International Joint Conference on Neural Networks (IEEE IJCNN 2012), 3070-3077 June, Brisbane, Australia.
  22. Alonso, E. and Mondragon, E. (2012). Uses, Abuses and Misuses of Computational Models in Classical Conditioning. 11th International Conference on Cognitive Modeling (ICCM-12), 96-100 April, Berlin, Germany.
  23. Alonso, E., Fairbank, M. and Mondragon, E. (2012). Conditioning for Least Action. 11th International Conference on Cognitive Modeling (ICCM-12), 234-239 April, Berlin, Germany.

Journal Article (17)

  1. Luzardo, A., Rivest, F., Alonso, E. and Ludvig, E.A. (2016). A drift-diffusion model of interval timing in the peak procedure. Journal of Mathematical Psychology . doi:10.1016/j.jmp.2016.10.002.
  2. Alonso, E., Fairbank, M. and Mondragon, E. (2015). Back to Optimality: A Formal Framework to Express the Dynamics of Learning Optimal Behavior. Adaptive Behavior, 23(4), pp. 206–215. doi:10.1177/1059712315589355.
  3. Fu, X., Li, S., Fairbank, M., Wunsch, D. and Alonso, E. (2015). Training Recurrent Neural Networks with the Levenberg–Marquardt Algorithm for Optimal Control of a Grid-Connected Converter. IEEE Transactions on Neural Networks and Learning Systems, 26(9), pp. 1900–1912. doi:10.1109/TNNLS.2014.2361267.
  4. Fairbank, M., Li, S., Fu, X., Alonso, E. and Wunsch, D. (2014). An Adaptive Recurrent Neural-Network Controller using a Stabilization Matrix and Predictive Inputs to Solve the Tracking Problem under Disturbances. Neural Networks, 49, pp. 74–86. doi:10.1016/j.neunet.2013.09.010.
  5. Mondragon, E., Gray, J., Alonso, E., Bonardi, C. and Jennings, D. (2014). SSCC TD: A Serial and Simultaneous Configural-Cue Compound Stimuli Representation for Temporal Difference Learning. PLoS ONE, 9(7): e102469 . doi:10.1371/journal.pone.0102469.
  6. Li, S., Fairbank, M., Johnson, C., Wunsch, D.C., Alonso, E. and Proano, J.L. (2014). Artificial Neural Networks for Control of a Grid-Connected Rectifier/Inverter under Disturbance, Dynamic and High Frequency Switching Conditions. IEEE Transactions on Neural Networks and Learning Systems, 25(4), pp. 738–750. doi:10.1109/TNNLS.2013.2280906.
  7. Teichmann, J., Broom, M. and Alonso, E. (2014). The Evolutionarily Dynamics of Aposematism: a Numerical Analysis of Co-Evolution in Finite Populations. Mathematical Modelling of Natural Phenomena (MMNP), 9(3), pp. 148–164. doi:10.1051/mmnp/20149310.
  8. Fairbank, M., Prokhorov, D. and Alonso, E. (2014). Clipping in Neurocontrol by Adaptive Dynamic Programming. IEEE Transactions on Neural Networks and Learning Systems, 25(10), pp. 1909–1920. doi:10.1109/TNNLS.2014.2297991.
  9. Mondragon, E., Alonso, E., Fernandez, A. and Gray, J. (2013). An Extension of the Rescorla and Wagner simulator for Context Conditioning. Computer Methods and Programs in Biomedicine, 110(2), pp. 226–230. doi:10.1016/j.cmpb.2013.01.016.
  10. Mondragon, E., Gray, J. and Alonso, E. (2013). A Complete Serial Compound Temporal Difference Simulator for Compound stimuli, Configural cues and Context representation. NeuroInformatics, 11(2), pp. 259–261. doi:10.1007/s12021-012-9172-z.
  11. Jennings, D., Alonso, E., Mondragon, E., Frassen, M. and Bonardi, C. (2013). The Effect of Stimulus Distribution Form on the Acquisition and Rate of Conditioned Responding: Implications for Theory. Journal of Experimental Psychology: Animal Behavior Processes, 39(3), pp. 233–248. doi:10.1037/a0032151.
  12. Teichmann, J., Broom, M. and Alonso, E. (2013). The Application of Temporal Difference Learning in Optimal Diet Models. Journal of Theoretical Biology, 340(7), pp. 11–16. doi:10.1016/j.jtbi.2013.08.036.
  13. Fairbank, M., Alonso, E. and Prokhorov, D. (2013). An Equivalence Between Adaptive Dynamic Programming With a Critic and Backpropagation Through Time. IEEE Transactions on Neural Networks and Learning Systems, 24(12), pp. 2088–2100. doi:10.1109/TNNLS.2013.2271778.
  14. Alonso, E. and Schmajuk, N. (2012). Computational Models of Classical Conditioning guest editors’ introduction. Learning and Behavior, 40(3), pp. 231–240. doi:10.3758/s13420-012-0081-7.
  15. Alonso, E., Mondragon, E. and Fernandez, A. (2012). A Java simulator of Rescorla and Wagner's prediction error model and configural cue extensions. Computer Methods and Programs in Biomedicine, 108(1), pp. 346–355. doi:10.1016/j.cmpb.2012.02.004.
  16. Fairbank, M., Alonso, E. and Prokhorov, D. (2012). Simple and Fast Calculation of the Second Order Gradients for Globalized Dual Heuristic Programming in Neural Networks. IEEE Transactions on Neural Networks and Learning Systems, 23(10), pp. 1671–1676. doi:10.1109/TNNLS.2012.2205268.
  17. Fairbank, M. and Alonso, E. (2012). Efficient Calculation of the Gauss-Newton Approximation of the Hessian Matrix in Neural Networks. Neural Computation, 24(3), pp. 607–610. doi:10.1162/NECO_a_00248.

Find us

City, University of London

Northampton Square

London EC1V 0HB

United Kingdom

Back to top

City, University of London is an independent member institution of the University of London. Established by Royal Charter in 1836, the University of London consists of 18 independent member institutions with outstanding global reputations and several prestigious central academic bodies and activities.