Xin Yao's Research Interests: Evolutionary Artificial Neural Networks

Evolutionary artificial neural networks (EANNs) refer to a special class of artificial neural networks (ANNs) in which evolution is another fundamental form of adaptation in addition to learning. Evolutionary algorithms (EAs) can be used to perform various tasks, such as connection weight training, architecture design, learning rule adaptation, input feature selection, connection weight initialization, rule extraction from ANNs, etc. One distinct feature of EANNs is their adaptability to a dynamic environment. In other words, EANNs can adapt to an environment as well as changes in the environment. The two forms of adaptation, i.e., evolution and learning in EANNs make their adaptation to a dynamic environment much more effective and efficient. In a broader sense, EANNs can be regarded as a general framework for adaptive systems, i.e., systems that can change their architectures and learning rules appropriately without human intervention.

At present, I am particularly interested in evolving neural network ensembles that will cooperate with each other to perform a common task. This work is supported and partially funded by BT (British Telecom) and EPSRC.

Selected Papers

1. Y. Liu and X. Yao, ``Learning and Evolution by Minimization of Mutual Information,'' Proc. of the 7th International Conference on Parallel Problem Solving from Nature (PPSN VII), Lecture Notes in Computer Science, Vol. 2439, Springer, September 2002, pp.495-504.

2. X. Yao and Y. Liu, ``From evolving a single neural network to evolving neural network ensembles,'' In Advances in the Evolutionary Synthesis of Intelligent Agents, Mukesh J. Patel, Vasant Honavar and Karthik Balakrishnan (eds.), Chapter 14, pp.383-427, The MIT Press, Cambridge, MA, 2001. (ISBN 0-262-16201-6)

3. Y. Liu, X. Yao and T. Higuchi, ``Evolutionary Ensembles with Negative Correlation Learning,'' IEEE Transactions on Evolutionary Computation, 4(4):380-387, November 2000.
   Available as TEC391_final.ps.gz.

4. X. Yao, ``Evolving artificial neural networks,'' Proceedings of the IEEE, 87(9):1423-1447, September 1999.
   Available as yao_ie3proc_online.ps.gz.

5. X. Yao and Y. Liu, ``Making use of population information in evolutionary artificial neural networks,'' IEEE Transactions on Systems, Man and Cybernetics, Part B: Cybernetics, 28(3):417-425, June 1998.
   Available as smc096-05-0503.ps.gz.

6. X. Yao and Y. Liu, ``Towards designing artificial neural networks by evolution,'' Applied Mathematics and Computation, 91(1):83-90, April 1998.
   Available as yao_liu_amc.ps.gz.

7. X. Yao and Y. Liu, ``A new evolutionary system for evolving artificial neural networks,'' IEEE Transactions on Neural Networks, 8(3):694-713, May 1997.
   Available as tnn2770.ps.gz.

8. Y. Liu and X. Yao (1996), ``A population-based learning algorithm which learns both architectures and weights of neural networks,'' Chinese Journal of Advanced Software Research (Allerton Press, Inc., New York, NY 10011), 3(1):54-65, 1996.
   Available as sc_workshop_paper.ps.Z.

9. X. Yao, Y. Liu and P. Darwen, ``How to make best use of evolutionary learning,'' Complexity International: An Electronic Journal of Complex Systems Research (ISSN 1320-0682), Vol. 3, July 1996.
   Also appeared in paper form in Complex Systems --- From Local Interactions to Global Phenomena, IOS Press, Amsterdam, pp.229--242, 1996.
   Available as yao_liu_darwen_cs96.ps.gz.

10. Y. Liu and X. Yao, ``Towards designing neural network ensembles by evolution,'' Proc. of the Fifth International Conference on Parallel Problem Solving from Nature (PPSN-V), Lecture Notes in Computer Science, Vol. 1498, A. E. Eiben, T. B{\"{a}}ck, M. Schoenauer and H.-P. Schwefel (ed.), Springer-Verlag, Berlin, pp.623-632, 1998.
    Available as liu_yao_ppsn98.ps.gz.

11. X. Yao, ``The importance of maintaining behavioural link between parents and offspring,'' Proc. of 1997 IEEE International Conference on Evolutionary Computation (ICEC'97), 13-16 April 1997, Indianapolis, USA, pp.629--633.
    Available as yao_icec97.ps.gz.

12. Y. Liu and X. Yao, ``Evolving modular neural networks which generalise well,'' Proc. of 1997 IEEE International Conference on Evolutionary Computation (ICEC'97), 13-16 April 1997, Indianapolis, USA, pp.605--610.
    Available as liu_yao_icec97.ps.gz.

13. X. Yao and Y. Liu, ``EPNet for chaotic time-series prediction,'' In Simulated Evolution and Learning, X. Yao, J.-H. Kim and T. Furuhashi (eds.), Lecture Notes in Artificial Intelligence, Vol. 1285, pp.146-156, Springer-Verlag, Berlin, 1997.
    Also in Proc. of the First Asia-Pacific Conference on Simulated Evolution And Learning (SEAL'96), Taejon, Korea, 9-12 November 1996, pp.331-342.
    Available as yao_liu_seal96.ps.gz.

14. X. Yao and Y. Liu (1996d), ``Ensemble Structure of Evolutionary Artificial Neural Networks,'' Proc. of the Third IEEE International Conference on Evolutionary Computation (ICEC'96), Nagoya, Japan, 20-22 May 1996, pp.659-664.
    (Available as yao_liu_icec96.ps.Z).

15. Y. Liu and X. Yao, ``Evolutionary design of artificial neural networks with different node transfer functions,'' Proc. of the Third IEEE International Conference on Evolutionary Computation (ICEC'96), Nagoya, Japan, 20-22 May 1996, pp.670-675.
    (Available as liu_yao_icec96.ps.Z).

16. X. Yao and Y. Liu, ``Towards Designing Artificial Neural Networks by Evolution,'' Proc. of the International Symposium on Artificial Life and Robotics (AROB), B-Con Plaza, Beppu, Oita, Japan, 18-20 February 1996, pp.265-268.
    (Available as yao_arob96.ps.Z).

17. X. Yao and Y. Liu, ``Evolving artificial neural networks through evolutionary programming,'' Presented at the Fifth Annual Conference on Evolutionary Programming, 29 February -- 2 March 1996, San Diego, CA, USA. pp.257-266, the MIT Press.
    (Available as ep96_eann_crc.ps.Z).

18. X. Yao and Y. Liu (1996c), ``Evolutionary artificial neural networks that learn and generalise well,'' Proc. of the 1996 IEEE International Conference on Nueural Networks (ICNN'96), Volume on Plenary, Panel and Special Sessions, pp.159-164, Sheraton Washington Hotel, Washington, DC, USA, 3-6 June 1996.
    (Available as yao_icnn96.ps.Z).

19. X. Yao (1993a), ``A review of evolutionary artificial neural networks,'' International Journal of Intelligent Systems, 8(4):539--567.
    Available as ijis.ps.Z.

20. X. Yao (1991c), ``Evolution of connectionist networks,'' Preprints of the Symp. on AI, Reasoning, and Creativity, ed. T. Dartnall, Brisbane, pp.49-52.

Last update: 5 September 2000