Andrea Soltoggio


School of Computer Science
University of Birmingham
Birmingham. B15 2TT
United Kingdom
Office:117
Phone: +44 (0)121 414 3707
Email: A.Soltoggio ( at ) cs.bham.ac.uk

My research is focused on computational models of neuromodulation and the analysis of their properties.
Neuromodulation is a form of synaptic plasticity -- named heterosynaptic -- that involves chemicals such as Acetylcholine, Dopamine, Norepinephrine and Serotonin. Experimental evidence suggests that neuromodulation is the working mechanism for learning, memory and motivation in human and animal behaviour. Computational models of modulatory systems can help understanding the underlying mechanisms of complex neural functions. The implementation of modulatory systems could prove effective for Robotics and adaptive, learning agents.

The subject draws inspiration from Neuroscience and Computational Neuroscience, Evolutionary Robotics, Evolutionary Computation, Intelligent Control, Adaptive Behaviour, Artificial Life.


Member of IEEE since 2004.

• Andrea Soltoggio and Ben Jones (2009) Novelty of Behaviour as a Basis for the Neuro-evolution of Operant Reward Learning Genetic and Evolutionary Computation Conference 2009, 8th-12th July, Montréal, Canada. (to appear) pdf.
  
  
• Andrea Soltoggio (2008) Evolutionary and Computational Advantages of Neuromodulated Plasticity Ph.D. thesis. University of Birmingham, UK. October 2008. pdf
  
  
• Andrea Soltoggio (2008) Neural Plasticity and Minimal Topologies for Reward-based Learning In the proceedings of the 8th International Conference on Hybrid Intelligent Systems,10th-12th September 2008. Barcellona, Spain. pdf.
  
  
• Soltoggio, A., Bullinaria, A. J., Mattiussi, C., Dürr, P. and Floreano, D. (2008) Evolutionary Advantages of Neuromodulated Plasticity in Dynamic, Reward-based Scenarios. Proceedings of Artificial Life XI Conference pdf.
  
  
• Dürr, P., Mattiussi, C., Soltoggio, A. and Floreano, D, (2008) Evolvability of Neuromodulated Learning for Robots. Symposium on Bio-inspired Learning and Intelligent Systems for Security, (BLISS) August 2008, Edinburgh, UK.
  
  
• Andrea Soltoggio (2008) Neuromodulation Increases Decision Speed in Dynamic Environments Proceedings of the 8th International Conference on Epigenetic Robotics, July 2008, Southampton, UK. pdf
  
  
• Andrea Soltoggio (2008) Phylogenetic Onset and Dynamics of Neuromodulation in Learning Neural Models. Experiments Meet Theory: Integrated Approaches to Neuroscience, Young Physiologists' Symposium, July 2008, Cambridge, UK. pdf
  
  
• Soltoggio, A., Dürr, P., Mattiussi, C., and Floreano, D. (2007) Evolving Neuromodulatory Topologies for Reinforcement Learning-like Problems. Proceedings of the 2007 IEEE Congress on Evolutionary Computation. 25-28 September 2007, Singapore. pdf
  
  
• Andrea Soltoggio: Does Learning Elicit Neuromodulation? Evolutionary Search in Reinforcement Learning-like Environments, Dynamics of Learning Behavior and Neuromodulation Workshop, European Congress on Artificial Life (ECAL 2007) 10-14 September 2007, Lisbon, Portugal. poster pdf, extended abstract pdf
  
  
• Andrea Soltoggio: A Simple Line Search Operator for Ridged Landscapes. Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2006), July 2006, Seattle, WA, USA. pdf
  
  
• Andrea Soltoggio: An Enhanced GA to Improve the Search Process Reliability in Tuning of Control Systems , Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2005), June 2005, Washington, DC, USA. pdf
  
  
• Andrea Soltoggio: "GP and GA in the Design of a Constrained Control System with Disturbance Rejection", Proceedings of the International Symposium on Intelligent Control, (ISIC 2004), 1-4 Semptember 2004, Taipei, Taiwan. Pdf.
  
  
• Andrea Soltoggio: A Comparison of Genetic Programming and Genetic Algorithms in the Design of a Robust, Saturated Control System, Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2004), June 2004, Seattle, WA, USA. pdf
  
  
• Andrea Soltoggio: A Case Study of GP and GAs in the Design of a Control System, GECCO 2004 Graduate Student Workshop Proceedings, June 2004, Seattle, USA.
  
  
• MSc Thesis. NTNU, June 2004, Evolutionary Algorithms in the Design and Tuning of a Control System. Pdf.
  
  
• Fordypningsprosjekt. Department of Computer and Information Science, NTNU.
  A Case Study of a Genetically Evolved Control System, November 2003
  Full version (pdf file, 844Kb)

• Uncertain foraging environments for simulated flying bees
  

  This experiment was used in my CEC 2007 and HIS 2008 papers. The flight simulation was implemented in C++ without graphical interface. If you are interested in running similar experiments, please email me and I'll be happy to send the code.

  
  
• Learning agents in T-mazes
  

  The code in C++ is available to reproduce the experiments presented in my ALife XI paper.

  
  
• Emergent modulatory topologies
  

  Emergent modulatory neurons and topologies are sought in the above enviroments by means of unconstrained evolutionary search on neural topologies. Highly adaptive and learning networks evolve autonomously to match the requirements in the environments. The C++ code used for the Alife XI and Epigenetic Robotics 2008 papers is available on request.

  
  
  
  
• Analog Genetic Econding
  The topology search in my CEC 2007 paper was conducted using the algorithm AGE. For further information on AGE, please see the website of the Laboratory of Intelligent Systems at EPFL where the algorithm was developed.

2007-2008

• 06-06991 Research Skills
  • Lectures
    L2 : Literature Searching and Review,
    L3 : Literature Searching and Review,
    L4 : Organized and Systematic Literature Search,
    L10 : Writing,
    L11 : Writing Abstracts,
    L12 : Referencing,
    L13 : Presentation Skills,
    L14 : Presentation Skills II,
    L15 : Work Management
  • Search engines and catalogues
  • Richard Hamming, You and Your Research
• 06-02411 Evolutionary Computation and 06-12414 Introduction to Evolutionary Computation
  • Lecture (15 Oct): Real-valued function optimisation in Evolutionary Computation: A brief overview.
  • Lecture (19 Nov) Evolutionary Algorithms in Control System Engineering
  • (1+1)EA example codes
• 06-18186 Design & Media Team

• 06-18186 Design & Media Team
• 06-18187 Foundations of Computer Science

• 06-02411 Evolutionary Computation and 06-12414 Introduction to Evolutionary Computation
• 06-12412 Introduction to Neural Computation
  • Perceptron Learning Rule Demo: applet.
• 06-18184 Artificial Intelligence & Cognitive Science Module web page

• 06-18184 Artificial Intelligence & Cognitive Science
• 06-08775 Introduction to Artificial Intelligence
• 06-02411 and 06-12414 Evolutionary Computation

• or www.bookfinder.com
  
  
• 
  
  
• phdwhat.net : The blook on PhD and not, what?
  
  
• My personal home page
  
  

I was born in Valtellina (town of Tirano), a valley of the Italian Alps. I studied at Politecnico di Milano. In the summer of 2002 I moved to the crisp air of Trondheim (Norway) where I continued my studies at the Norwegian University of Science and Technology (NTNU) as T.I.M.E student (Top Industrial Managers for Europe, double degree programme). Time went by quite fast, and after two great years in Norway, I ended up in Birmingham (UK), where I study and work at The University of Birmingham, School of Computer Science. From June 2006 to December 2006 I was at the Laboratory of Intelligent Systems (LIS) at EPFL, Lausanne, Switzerland.