People
  1. Students
  2. Alumni
  3. Honorary Graduates
  4. Academic Experts
  1. Michael Fairbank
People

Contact Information

Contact

Postal Address

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

About

Background

I am a computer scientist specialising in Neural Networks and Adaptive Dynamic Programming.

Qualifications

BSc Mathematical Physics, 1994, Nottingham University
MSc Knowledge Based Systems, 1995, Edinburgh University
PhD Computer Science, 2014, City University London

Employment

Head of Mathematics and Computing Faculty at DLD College London

Research

Neural Networks

I specialise in applying Recurrent Neural Networks to control problems, and financial forecasting.

Adaptive Dynamic Programming

Adaptive Dynamic Programming is a branch of Reinforcement Learning. My PhD Thesis was on Value-Gradient Learning.

Power System Controllers

I have worked on a Grid Connected Converter device that is controlled by a recurrent Neural Network. This project won first prize in the ICT-Labs Smart-Energy Ideas Challenge, in Berlin 2014.

Optimization Algorithms

I am working on variations of optimization algorithms for training neural networks.

Publications

Chapter

  1. 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.

Conference Papers and Proceedings (5)

  1. Li, S., Fu, X., Alonso, E., Fairbank, M. and Wunsch, D.C. (2016). Neural-network based vector control of VSCHVDC transmission systems. .
  2. Li, S., Fairbank, M., Fu, X., Wunsch, D.C. and Alonso, E. (2013). Nested-loop neural network vector control of permanent magnet synchronous motors. .
  3. Alonso, E. and Fairbank, M. (2013). Emergent and adaptive systems of systems. .
  4. Li, S., Fairbank, M., Wunsch, D.C. and Alonso, E. (2012). Vector control of a grid-connected rectifier/inverter using an artificial neural network. .
  5. Fairbank, M. and Alonso, E. (2012). Value-gradient learning. .

Journal Articles (10)

  1. Fu, X., Li, S., Fairbank, M., Wunsch, D.C. 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.
  2. Alonso, E., Fairbank, M. and Mondragón, 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. 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.
  4. Li, S., Fairbank, M., Johnson, C., Wunsch, D.C., Alonso, E. and Proao, J.L. (2014). Artificial neural networks for control of a grid-Connected rectifier/inverter under disturbance, dynamic and power converter switching conditions. IEEE Transactions on Neural Networks and Learning Systems, 25(4), pp. 738–750. doi:10.1109/TNNLS.2013.2280906.
  5. 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 a tracking problem under disturbances. Neural Networks, 49, pp. 74–86. doi:10.1016/j.neunet.2013.09.010.
  6. 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.
  7. Fairbank, M., Alonso, E. and Prokhorov, D. (2012). Simple and fast calculation of the second-order gradients for globalized dual heuristic dynamic programming in neural networks. IEEE Transactions on Neural Networks and Learning Systems, 23(10), pp. 1671–1676. doi:10.1109/TNNLS.2012.2205268.
  8. Fairbank, M. and Alonso, E. (2012). The divergence of reinforcement learning algorithms with value- iteration and function approximation. Proceedings of the International Joint Conference on Neural Networks . doi:10.1109/IJCNN.2012.6252792.
  9. Fairbank, M. and Alonso, E. (2012). A comparison of learning speed and ability to cope without exploration between DHP and TD(0). Proceedings of the International Joint Conference on Neural Networks . doi:10.1109/IJCNN.2012.6252569.
  10. 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.

Thesis/Dissertation

  1. Fairbank, Value-Gradient Learning. (PhD Thesis)

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.