Now showing items 3-16 of 16

  • Evolution and devolved action: towards the evolution of systems. 

    Macleod, Christopher; McMinn, David; Reddipogu, Ann; Capanni, Niccolo Francesco; Maxwell, Grant M. (Robert Gordon University, 2001)
    MACLEOD, C., MCMINN, D., REDDIPOGU, A. B., CAPANNI, N. F. and MAXWELL, G. M., 2001. Evolution and devolved action: towards the evolution of systems. In: Appendix B of MCMINN, D. Using evolutionary artificial neural networks to design hierarchical animat nervous systems, Ph. D. thesis. Aberdeen : Robert Gordon University.
    The Artificial Neural Networks group at the Robert Gordon University has, over the last six years, built up considerable knowledge and practical experience in Evolutionary Artificial Neural Networks. This experience ...
  • The evolution of modular artificial neural networks 

    Muthuraman, Sethuraman (The Robert Gordon University School of Engineering, 2005)
    This thesis describes a novel approach to the evolution of Modular Artificial Neural Networks. Standard Evolutionary Algorithms, used in this application include: Genetic Algorithms, Evolutionary Strategies, Evolutionary ...
  • Evolutionary algorithms for real-time artificial neural network training. 

    Jagadeesan, Ananda Prasanna; Maxwell, Grant M.; Macleod, Christopher (Springer https://dx.doi.org/10.1007/11550907_12, 2005-09-01)
    JAGADEESAN, A., MAXWELL, G. and MACLEOD, C. 2005. Evolutionary algorithms for real-time artificial neural network training. Lecture notes in computer science [online], 3697, Proceedings of the 15th international conference on artifical neural networks (ICANN 2005): formal models and their applications, 11-15 September 2005, Warsaw, Poland, part 2, pages 73-78. Available from: https://dx.doi.org/10.1007/11550907_12
    This paper reports on experiments investigating the use of Evolutionary Algorithms to train Artificial Neural Networks in real time. A simulated legged mobile robot was used as a test bed in the experiments. Since the ...
  • The functionality of spatial and time domain artificial neural models 

    Capanni, Niccolo Francesco (The Robert Gordon University School of Engineering, 2006-08)
    This thesis investigates the functionality of the units used in connectionist Artificial Intelligence systems. Artificial Neural Networks form the foundation of the research and their units, Artificial Neurons, are first ...
  • Incremental growth in modular neural networks. 

    Macleod, Christopher; Maxwell, Grant M.; Muthuraman, Sethuraman (Elsevier http://dx.doi.org/10.1016/j.engappai.2008.11.002, 2009-06)
    MACLEOD, C., MAXWELL, G. M., and MUTHURAMAN, S., 2009. Incremental growth in modular neural networks. Engineering Applications of Artificial Intelligence, 22 (4/5), pp. 660-666.
    This paper outlines an algorithm for incrementally growing Artificial Neural Networks. The algorithm allows the network to expand by adding new sub-networks or modules to an existing structure; the modules are trained using ...
  • Minds for robots. 

    Macleod, Christopher; Maxwell, Grant M. (St. John Patrick Publishers Ltd., 2009-01)
    MACLEOD, C. and MAXWELL, G. M., 2009. Minds for robots. Electronics World, 115 (1873), pp. 16-19.
    In the 1950s and 60s, popular culture was entranced by robots. There was Robby in “Forbidden Planet,” Gort in “The day the Earth stood still” and many others. This fascination has continued to the present day, only the ...
  • The monitoring of induction motor starting transients with a view to early fault detection. 

    Elder, Stewart (The Robert Gordon University School of Engineering, 1992-03)
    The aim of this work is to investigate the possibility of detecting faults in a 3 phase Induction motor by monitoring and analysing the transient line current waveform during the starting period. This is a particularly ...
  • Real time evolutionary algorithms in robotic neural control systems. 

    Jagadeesan, Ananda Prasanna (The Robert Gordon University School of Engineering, 2006)
    This thesis describes the use of a Real-Time Evolutionary Algorithm (RTEA) to optimise an Artificial Neural Network (ANN) on-line (in this context “on-line” means while it is in use). Traditionally, Evolutionary Algorithms ...
  • A sensory system for robots using evolutionary artificial neural networks. 

    Reddipogu, Ann (Robert Gordon University School of Engineering., 2006-08)
    The thesis presents the research involved with developing an Intelligent Vision System for an animat that can analyse a visual scene in uncontrolled environments. Inspiration was drawn both from Biological Visual Systems ...
  • The synthesis of artificial neural networks using single string evolutionary techniques. 

    Macleod, Christopher (The Robert Gordon University School of Electronic and Electrical Engineering, 1999)
    The research presented in this thesis is concerned with optimising the structure of Artificial Neural Networks. These techniques are based on computer modelling of biological evolution or foetal development. They are ...
  • Training neural networks using Taguchi methods: overcoming interaction problems. 

    Viswanathan, Alagappan; Macleod, Christopher; Maxwell, Grant M.; Kalidindi, Sashank (Springer https://dx.doi.org/10.1007/11550907_17, 2005-09-01)
    VISWANATHAN, A., MACLEOD, C., MAXWELL, G. and KALIDINDI, S. 2005. Training neural networks using Taguchi methods: overcoming interaction problems. Lecture notes in computer science [online], 3697, Proceedings of the 15th international conference on artifical neural networks (ICANN 2005): formal models and their applications, 11-15 September 2005, Warsaw, Poland, part 2, pages 103-108. Available from: https://dx.doi.org/10.1007/11550907_17
    Taguchi Methods (and other orthogonal arrays) may be used to train small Artificial Neural Networks very quickly in a variety of tasks. These include, importantly, Control Systems. Previous experimental work has shown that ...
  • Using evolutionary artificial neural networks to design hierarchical animat nervous systems. 

    McMinn, David (The Robert Gordon University School of Engineering, 2001-12)
    The research presented in this thesis examines the area of control systems for robots or animats (animal-like robots). Existing systems have problems in that they require a great deal of manual design or are limited to ...
  • Using orthogonal arrays to train artificial neural networks. 

    Viswanathan, Alagappan (The Robert Gordon University School of Engineering, 2005-10)
    The thesis outlines the use of Orthogonal Arrays for the training of Artificial Neural Networks. Such arrays are popularly used in system optimisation and are known as Taguchi Methods. The chief advantage of the method is ...
  • Vision systems for a mobile robot based on line detection using the Hough Transform and artificial neural networks. 

    Damaryam, Gideon Kanji (The Robert Gordon University School of Engineering, 2008-11)
    This project contributes to the problem of mobile robot self-navigation within a rectilinear framework based on visual data. It proposes a number of vision systems based on detection of straight lines in images captured ...