- Najibi, F., Apostolopoulou, D. and Alonso, E. (2021). Enhanced performance Gaussian process regression for probabilistic short-term solar output forecast. International Journal of Electrical Power & Energy Systems, 130, pp. 106916–106916. doi:10.1016/j.ijepes.2021.106916.
- Rozada, S., Apostolopoulou, D. and Alonso, E. (2021). Deep multi‐agent Reinforcement Learning for cost‐efficient distributed load frequency control. IET Energy Systems Integration, 3(3), pp. 327–343. doi:10.1049/esi2.12030.
- Ananda, A., Ngan, K.H., Karabağ, C., Ter-Sarkisov, A., Alonso, E. and Reyes-Aldasoro, C.C. (2021). Classification and Visualisation of Normal and Abnormal Radiographs; A Comparison between Eleven Convolutional Neural Network Architectures. Sensors, 21(16), pp. 5381–5381. doi:10.3390/s21165381.
- Najibi, F., Apostolopoulou, D. and Alonso, E. (2021). TSO-DSO Coordination Schemes to Facilitate Distributed Resources Integration. Sustainability, 13(14), pp. 7832–7832. doi:10.3390/su13147832.
- Fu, X., Li, S., Wunsch, D.C. and Alonso, E. (2021). Local Stability and Convergence Analysis of Neural Network Controllers With Error Integral Inputs. IEEE Transactions on Neural Networks and Learning Systems pp. 1–13. doi:10.1109/tnnls.2021.3116189.
- Mondragon, E., Alonso, E. and Kokkola, K. (2020). Associative Learning Should Go Deep. Trends in Cognitive Sciences, 21(11), pp. 822–825. doi:10.1016/j.tics.2017.06.001.
- Lambrechts, A., Cook, J., Ludvig, E., Alonso, E., Anns, S., Taylor, M. … Gaigg, S. (2020). Reward devaluation in autistic children and adolescents with complex needs: a feasibility study. Autism Research, 13(11), pp. 1915–1915. doi:10.1002/aur.2388.
- Li, S., Won, H., Fu, X., Fairbank, M., Wunsch, D. and Alonso, E. (2020). Neural-Network Vector Controller for Permanent-Magnet Synchronous Motor Drives: Simulated and Hardware-Validated Results. IEEE Transactions on Cybernetics, 50(7), pp. 3218–3230. doi:10.1109/TCYB.2019.2897653.
- Bauer, J., Broom, M. and Alonso, E. (2019). The stabilization of equilibria in evolutionary game dynamics through mutation: mutation limits in evolutionary games. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 475(2231), pp. 20190355–20190355. doi:10.1098/rspa.2019.0355.
- Carrera, Á., Alonso, E. and Iglesias, C.A. (2019). A Bayesian Argumentation Framework for Distributed Fault Diagnosis in Telecommunication Networks. Sensors, 19(15). doi:10.3390/s19153408.
- Kokkola, N., Mondragon, E. and Alonso, E. (2019). A Double Error Dynamic Asymptote Model of Associative Learning. Psychological Review, 126(4), pp. 506–549. doi:10.1037/rev0000147.
- Riaz, A., Asad, M., Alonso, E. and Slabaugh, G.G. (2018). Fusion of fMRI and Non-Imaging Data for ADHD Classification. Computerized Medical Imaging and Graphics, 65, pp. 115–128. doi:10.1016/j.compmedimag.2017.10.002.
- Basaru, R.R., Child, C., Alonso, E. and Slabaugh, G. (2018). Data-driven Recovery of Hand Depth using Conditional Regressive Random Forest on Stereo Images. IET Computer Vision. doi:10.1049/iet-cvi.2017.0227.
- Luzardo, A., Rivest, F., Alonso, E. and Ludvig, E. (2017). A Drift-Diffusion Model of Interval Timing in the Peak Procedure. Journal of Mathematical Psychology, 77, pp. 111–123. doi:10.1016/j.jmp.2016.10.002.
- Albrecht, T., Slabaugh, G., Alonso, E. and Al-Arif, M.R. (2017). Deep Learning for Single-Molecule Science. Nanotechnology, 28(42), pp. 423001–423001. doi:10.1088/1361-6528/aa8334.
- Luzardo, A., Alonso, E. and Mondragon, E. (2017). A Rescorla-Wagner Drift-Diffusion Model of Conditioning and Timing. PLoS Computational Biology, 13(11), pp. 1–1. doi:10.1371/journal.pcbi.1005796.
- Guimera Busquets, J., Alonso, E. and Evans, A. (2017). Air Itinerary Shares Estimation Using Multinomial Logit Models. Transportation Planning and Technology, 41(1), pp. 3–16. doi:10.1080/03081060.2018.1402742.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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, pp. 1–1. doi:10.1371/journal.pone.0102469.
- Alonso, E. and Mondragón, E. (2014). What Have Computational Models Ever Done for Us?: A Case Study in Classical Conditioning. International Journal of Artificial Life Research (IJALR), 4(1), pp. 1–12.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- Tarela, J.M., Basterretxea, K., del Campo, I., Martínez, M.V. and Alonso, E. (2002). Optimised PWL recursive approximation and its application to neuro-fuzzy systems. Mathematical and Computer Modelling, 35(7-8), pp. 867–883. doi:10.1016/s0895-7177(02)00056-0.
- Decker, K., Fisher, M., Luck, M., Tennenholtz, M. and UKMAS'98 Contributors, (1999). Continuing research in multi-agent systems. The Knowledge Engineering Review, 14(3), pp. 279–283. doi:10.1017/s026988899900301x.
- Tarela, J.M., Alonso, E. and Martínez, M.V. (1990). A representation method for PWL functions oriented to parallel processing. Mathematical and Computer Modelling, 13(10), pp. 75–83. doi:10.1016/0895-7177(90)90090-a.
Dr Eduardo Alonso
Contact details
Address
Dr Eduardo Alonso
A304B,
College Building
City, University of London
Northampton Square
London EC1V 0HB
United Kingdom
Northampton Square
London EC1V 0HB
United Kingdom
About
Overview
I am the Director of the Artificial Intelligence Research Centre, CitAI, where we specialise in the intersection between the development of novel AI techniques, Explainable AI (XAI) and Artificial General Intelligence (AGI), with a keen interest in the legal, ethical and social impact of AI.
Research interests
(1) Computational modelling and simulation in neuroscience and evolutionary biology.
(2) Deep Learning architectures and algorithms for reinforcement learning and creativity.
(3) Mathematical (abstract algebra) models of emergence and adaptation.
(4) Industrial applications of AI, and AI social impact (legal, ethics).
Please notice that my Publications above are dated from 2012 only.
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.
Also contact me if you would like to know more about PhD scholarships under the EIT-Digital Industrial Artificial Intelligence Doctoral Training Program.
News
(1) Published "The Stabilization of Equilibria in Evolutionary Game Dynamics through Mutation: Mutation Limits in Evolutionary Games" in Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, with Johann Bauer and Mark Broom, https://doi.org/10.1098/rspa.2019.0355.
(2) Published "A Double Error Dynamic Asymptote Model of Associative Learning" in Psychological Review, with Niklas Kokkola and Esther Mondragon, https://doi.org/10.1037/rev0000147.
(3) Published "Neural-Network Vector Controller for Permanent-Magnet Synchronous Motor Drives: Simulated and Hardware-Validated Results" in IEEE Transactions on Cybernetics, with Shuhui Li, Hoyun Wo, Xingang Fu, Michael Fairbank and Donald C. Wunsch, https://doi.org/10.1109/TCYB.2019.2897653.
(4) Published "Associative Learning Should Go Deep" in Trends in Cognitive Sciences, with Dr Esther Mondragon and Niklas Kokkola, http://dx.doi.org/10.1016/j.tics.2017.06.001.
(5) Published "Deep Learning for Single-Molecule Science" in Nanotechnology, with T. Albrecht, G. Slabaugh, and M.R. Al-Arif, http://iopscience.iop.org/article/10.1088/1361-6528/aa8334.
(6) 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).
(7) 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).
(8) 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.
(9) 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.
(10) 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.
(11) "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.
Qualifications
- BSc, MSc, PhD, University of the Basque Country, Spain
Memberships of committees
- Engineering and Physical Sciences Research Council, Jan 2009 – Dec 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
Alexandra Clay
Attendance: Oct 2021 – Sep 2025, full-time
Thesis title: Episodic Memory and Emotions in Artificial Systems and their Applications
Role: 1st Supervisor
Further information: Dr Esther Mondragon
Mpagi Kironde
Attendance: Apr 2021 – Mar 2025, full-time
Thesis title: Associative Learning using a Deep Neural Network based on Unsupervised Representation
Role: 2nd Supervisor
Further information: With Dr Esther Mondragon
Corina Catarau-Cotutiu
Attendance: Oct 2020 – present, full-time
Thesis title: Free Energy Principle for Adaptive Cognitive Architectures
Role: External Supervisor
Further information: With Dr Esther Mondragon and Dr Michael-Garcia Ortiz
Alexander W Dean
Attendance: Oct 2020 – present, full-time
Thesis title: Study of Algebraic Structures in Continual Representational Learning
Role: External Supervisor
Further information: With Dr Esther Mondragon, Dr Laure Daviaud and Dr Michael Garcia-Ortiz
Kiran Ikram
Attendance: Oct 2020 – present, part-time
Thesis title: Mixed Motive Multi Agent Learning Systems
Role: 1st Supervisor
Further information: With Dr Esther Mondragon and Dr Michael Garcia-Ortiz
Vince Jankovics
Attendance: Oct 2020 – present, full-time
Thesis title: Transfer Learning for Human-like Computing
Role: 1st Supervisor
Further information: With Dr Michael Garcia-Ortiz
Sami Saadaoui
Attendance: Oct 2020 – present, full-time
Thesis title: Using Ai Analytics to Close the Advice Gap for Life, Pension & Investments (LP&I)
Role: 1st Supervisor
Further information: With Dr Aram Ter-Sarkisov (sponsored by EIT-Digital & Ai London)
Alex McCaffrey
Attendance: Oct 2020 – present, full-time
Thesis title: Free Energy Principle as Drive for Adaptive Cognitive Architectures
Role: 1st Supervisor
Further information: With Dr Michael Garcia-Ortiz and Dr Esther Mondragon (sponsored by DSTL)
Abdul Basit Hafeez
Attendance: Feb 2020 – present, full-time
Thesis title: Algorithms for Predictive Maintenance of Vehicles in a Connected Environment
Role: 1st Supervisor
Further information: With Dr Michael Garcia-Ortiz (sponsored by EIT-Digital & Bosch)
Sarah Scott
Attendance: Oct 2019 – present, full-time
Thesis title: Towards Deep Understanding in Task-Oriented Dialogue Systems Using Deep Reinforcement Learning
Role: 1st Supervisor
Further information: With Dr Tillman Weyde
Esther Mulwa
Attendance: Jun 2019 – present, full-time
Thesis title: Building an Associative Model Using Deep Learning
Role: 1st Supervisor
Further information: With Dr. Esther Mondragon
Ananda Ananda
Attendance: Oct 2018 – present, full-time
Thesis title: Wrist fractures analysis in uncertainty pattern on x-ray imaging
Role: 2nd Supervisor
Further information: With Dr. Constantino Reyes Aldasoro
Fatemeh Najibi
Attendance: 2018 – present, full-time
Thesis title: Optimal Operation of Microgrids in the Presence of Renewable Generations such as Photovoltaic
Role: 1st Supervisor
Further information: With Dr. Dimitra Apostolopoulou
Rachel Townsend
Attendance: 2017 – present, part-time
Thesis title: Double Deep-Q Networks
Role: 2nd Supervisor
Further information: With Dr. Chris Child
Johann Bauer
Attendance: 2017 – present, full-time
Thesis title: The Modelling of Network Topologies under Evolutionary Dynamics
Role: 2nd Supervisor
Further information: With Prof. Mark Broom
Atif Riaz
Attendance: 2015 – present, full-time
Thesis title: Machine Learning for Functional Connectivity Analysis of Neurological Disorders Using Magnetic Resonance Imaging
Role: 1st Supervisor
Further information: With Dr. Greg Slabaugh
Nathan Olliverre
Attendance: 2015 – present, part-time
Thesis title: Semi-supervised Machine Learning Techniques for Identifying and Classifying Brain Tumours from MRI, MRS and 3D MRS imaging
Role: 1st Supervisor
Further information: With Dr. Constantino Reyes Aldasoro and Dr. Greg Slabaugh
Andre Luzardo
Attendance: 2014 – 2017
Thesis title: A Model for Timing and Learning
Further information: With Dr. Esther Mondragon
Konstantin Pozdniakov
Attendance: 2013 – 2018
Thesis title: Unsupervised Machine Learning in Cyber-Security
Further information: With Prof. Kevin Jones and Dr. Vladimir Stankovic
Remilekun Basaru
Attendance: 2013 – 2018
Thesis title: Robust Hand-pose Recognition from Egocentric Stereovision
Further information: With Dr. Greg Slabaugh and Dr. Chris Child
Niklas Kokkola
Attendance: 2013 – 2017
Thesis title: Computational Models of Learning and Behaviour
Further information: With Dr. Esther Mondragon
Judit Guimera-Busquets
Attendance: 2013 – present, part-time
Thesis title: Applying Machine Learning Techniques to Analyse Operational Flight Data
Role: 2nd Supervisor
Further information: With Prof. Chris Atkin and Dr. Antony Evans
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
Michael Fairbank
Attendance: 2011 – 2014
Thesis title: Value-Gradient Learning
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
Tshiamo Motshegwa
Attendance: 2005 – 2009
Thesis title: Distributed Termination Detection for Multiagent Protocols
Further information: With Prof. Michael Schroeder
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
Jack Gomoluch
Attendance: 2001 – 2005
Thesis title: Market-based Resource Allocation for Distributed Information Processing Applications
Further information: With Prof. Michael Schroeder
Marcus Pearce
Attendance: 2001 – 2005
Thesis title: Construction and Evaluation of Computational Models of Music Perception and Cognition
Further information: With Prof. Geraint Wiggins
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
Publications
Publications by category
Book
- 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.
Chapters (6)
- 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.
- 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.
- Alonso, E. and Mondragón, E. (2011). Computational Models of Learning and Beyond. Computational Neuroscience for Advancing Artificial Intelligence (pp. 316–332). IGI Global.
- Jennings, D.J., Alonso, E., Mondragón, E. and Bonardi, C. (2011). Temporal Uncertainty During Overshadowing. Computational Neuroscience for Advancing Artificial Intelligence (pp. 46–55). IGI Global.
- Alonso, E. and Mondragon, E. (2004). Agency, Learning and Animal-Based Reinforcement Learning. In Nickles, M., Rovatsos, M. and Weiss, G. (Eds.), Agents and Computational Autonomy: Potential, Risks, and Solutions (pp. 1–1). Berlin: Springer-Verlag.
- Fairbank, M., Prokhorov, D. and Alonso, E. Approximating Optimal Control with Value Gradient Learning. Reinforcement Learning and Approximate Dynamic Programming for Feedback Control (pp. 142–161). John Wiley & Sons, Inc..
Conference papers and proceedings (41)
- Ter-Sarkisov, A. and Alonso, E. (2022). Logo Generation Using Regional Features: A Faster R-CNN Approach to Generative Adversarial Networks.
- Hafeez, A.B., Alonso, E. and Ter-Sarkisov, A. (2021). Towards Sequential Multivariate Fault Prediction for Vehicular Predictive Maintenance. 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA) 13-16 December.
- Lewis, D., Zugarini, A. and Alonso, E. (2021). Syllable Neural Language Models for English Poem Generation. 12th International Conference on Computational Creativity (ICCC'21) 14-18 September, Mexico.
- Najibi, F., Apostolopoulou, D. and Alonso, E. (2021). Clustering Sensitivity Analysis for Gaussian Process Regression Based Solar Output Forecast. 2021 IEEE Madrid PowerTech 28 Jun 2021 – 2 Jul 2021.
- Ikram, K., Mondragon, E., Alonso, E. and Garcia-Ortiz, M. (2021). HexaJungle: a MARL Simulator to Study the Emergence of Language. Conference on Computer Vision and Pattern Recognition (CVPR 2021), Embodied AI Workshop 19-25 June, Nashville, TN (virtual).
- 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.
- Ananda, , Karabag, C., Ter-Sarkisov, A., Alonso, E. and Reyes-Aldasoro, C.C. (2020). Radiography Classification: A Comparison between Eleven Convolutional Neural Networks. 2020 Fourth International Conference on Multimedia Computing, Networking and Applications (MCNA) 19-22 October.
- Rozada, S., Apostolopoulou, D. and Alonso, E. (2020). Load Frequency Control: A Deep Multi-Agent Reinforcement Learning Approach. 2020 IEEE Power & Energy Society General Meeting (PESGM) 2-6 August.
- Pozdniakov, K., Alonso, E., Stankovic, V., Tam, K. and Jones, K. (2020). Smart Computer Security Audit: Reinforcement Learning with a Deep Neural Network Approximator. Cyber2020, 135-143 15-19 June, Dublin.
- de A. F. Mello, F.R., Apostolopoulou, D. and Alonso, E. (2020). Cost Efficient Distributed Load Frequency Control in Power Systems.
- Olliverre, N.J., Yang, G., Slabaugh, G.G., Reyes-Aldasoro, C.C. and Alonso, E. (2018). Generating Magnetic Resonance Spectroscopy Imaging Data of Brain Tumours from Linear, Non-Linear and Deep Learning Models. SASHIMI 2018: Simulation and Synthesis in Medical Imaging, LNCS 11037, 130-138 16-22 September, Granada, Spain.
- Najibi, F., Alonso, E. and Apostolopoulou, D. (2018). Optimal Dispatch of Pumped Storage Hydro Cascade under Uncertainty. Control 2018 – 12th International UKACC Conference on Control, 187-192 5-7 September, Sheffield, UK.
- Riaz, A., Asad, M., Al-Arif, S.M.M.R., Alonso, E., Dima, D., Corr, P. … Slabaugh, G. (2018). DeepFMRI: And End-to-End Deep Network for Classification of FRMI Data. 15th IEEE International Symposium on Biomedical Imaging, 1419-1422 April, Washington DC, USA.
- Basaru, R., Child, C., Alonso, E. and Slabaugh, G.G. (2018). Conditional Regressive Random Forest Stereo-based Hand Depth Recovery.
- Basaru, R., Child, C., Alonso, E. and Slabaugh, G.G. (2017). Hand Pose Estimation Using Deep Stereovision and Markov-chain Monte Carlo. International Conference on Computer Vision, Workshop on Observing and Understanding Hands in Action, 595-603 October, Venice, Italy.
- Teichmann, J., Alonso, E. and Broom, M. (2017). Reinforcement Learning as a Model of Aposematism. 13th International Conference on Artificial Evolution, 217-230 October, Paris, France.
- Teichmann, J., Alonso, E. and Broom, M. (2017). Reinforcement Learning is an Effective Strategy to Create Phenotypic Variation and a Potential Mechanism for the Initial Evolution of Learning. 13th International Conference on Artificial Evolution, 246-253 October, Paris, France.
- Riaz, A., Asad, M., Al-Arid, S.M.M.R., Alonso, E., Dima, D., Corr, P. … Slabaugh, G. (2017). FCNet: A Convolutional Neural Network for Calculating Functional Connectivity from functional MRI. 1st International Workshop on Connectomics in NeuroImaging (CNI), LNCS 10511, 70-78 September, Quebec City, QC, Canada.
- 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 November, Palermo, Italy.
- 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.
- 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, Vol. 3, 1537-1552 June, Washington, D.C.
- 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.
- Li, S., Fu, X., Jaithwa, I., Alonso, E., Fairbank, M. and C. Wunsch, D. (2015). Control of Three-Phase Grid-Connected Microgrids using Artificial Neural Networks. 7th International Conference on Neural Computation Theory and Applications 12-14 November.
- 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.
- 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.
- 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 October, Dallas, TX.
- 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.
- 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.
- Weller, P., Fernandez, A. and Alonso, E. (2014). Towards a Personalised Health System. 7th International Conference on Health Informatics (HEALTHINF 2014), pp. 256-261 3 Jun 2014 – 6 Mar 2014, Angers, France.
- Alonso, E. and Mondragon, E. (2014). Quantum Probability and Operant Conditioning: Behavioral Uncertainty in Reinforcement Learning. 6th International Conference on Agents and Artificial Intelligence (ICAART 2014), 2448-251 3-6 March, Angers, France.
- Alonso, E., Sahota, P. and Mondragon, E. (2014). Computational Models of Classical Conditioning: A Qualitative Evaluation and Comparison. 6th International Conference on Agents and Artificial Intelligence (ICAART 2014), 2445-247 3-6 March, Angers, France.
- 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.
- 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.
- 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.
- 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.
- 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.
- Fairbank, M. and Alonso, E. (2012). Value-Gradient Learning. IEEE International Joint Conference on Neural Networks (IEEE IJCNN 2012), 3062-3069 June, Brisbane, Australia.
- 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.
- 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.
- 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.
- 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.