• Publications
  • Influence
Artificial Intelligence: The Basics
'if AI is outside your field, or you know something of the subject and would like to know more then Artificial Intelligence: The Basics is a brilliant primer.' - Nick Smith, Engineering andExpand
The application of implant technology for cybernetic systems.
The response to stimulation improved considerably during the trial, suggesting that the subject learned to process the incoming information more effectively, and may allow recipients to have abilities they would otherwise not possess. Expand
Emergence of a Small-World Functional Network in Cultured Neurons
The functional network of cultures at mature ages is efficient and highly suited to complex processing tasks and points to complex intrinsic biological mechanisms. Expand
Neural network enhanced generalised minimum variance self-tuning controller for nonlinear discrete-time systems
A neural network enhanced self-tuning controller is presented, which combines the attributes of neural network mapping with a generalised minimum variance self-tuning control (STC) strategy. In thisExpand
Can machines talk? Comparison of Eliza with modern dialogue systems
An original experiment comparing five successful artificial dialogue systems with an online version of Eliza to find if current dialogue systems use the same, psychotherapist questioning technique as Joseph Weizenbaum's 1960 natural language understanding programme, Eliza, shows statistical significance shows these dialogue systems are an improvement on their predecessor. Expand
Neural network applications in control
This book discusses the development of dynamic artificial neural networks in state estimation and nonlinear process control, and the construction of nonlinear dynamical processes in these applications. Expand
Automatic nonlinear predictive model-construction algorithm using forward regression and the PRESS statistic
An automatic nonlinear predictive model-construction algorithm is introduced based on forward regression and the predicted-residual-sums-of-squares (PRESS) statistic that can achieve a fully automated procedure without resort to any other validation data set for iterative model evaluation. Expand
Strategies for feedback linearisation : a dynamic neural network approach
Using relevant mathematical proofs and case studies illustrating design and application issues, this book demonstrates the identification of nonlinear models without the complicated and costly development of models based on physical laws. Expand
Dynamic Niche Clustering: a fuzzy variable radius niching technique for multimodal optimisation in GAs
This paper describes the recent developments and improvements made to the variable radius niching technique called Dynamic Niche Clustering (DNC). DNC is fitness sharing based technique that employsExpand