Realising the promise of neural networks for practical optimisation: improving their efficiency and effectivess through chaotic dynamics and hardware implementation. Combinatorial optimisation problems such as transportation routing and assembly-line scheduling are critical to the efficiency of many industries, but their combinatorial explosion makes rapid solution difficult. Neural networks (NNs) hold much potential for rapid solution though hardware implementation, but we need to improve the q ....Realising the promise of neural networks for practical optimisation: improving their efficiency and effectivess through chaotic dynamics and hardware implementation. Combinatorial optimisation problems such as transportation routing and assembly-line scheduling are critical to the efficiency of many industries, but their combinatorial explosion makes rapid solution difficult. Neural networks (NNs) hold much potential for rapid solution though hardware implementation, but we need to improve the quality of their solutions before developing hardware. We have previously shown that the rich dynamics of chaos can improve the efficiency and effectiveness of NNs. We aim to develop new chaotic NN models, rigorously evaluate them on industrially significant problems such as those arising in manufacturing, logistics and telecommunications, and demonstrate their speed through hardware acceleration.Read moreRead less
Stochastic Geometry for Multi-sensor Data Fusion System. The aim of this project is to develop efficient algorithms for tracking and sensor management in a multi-sensor multi-target environment. Finite random set theory provides a natural way of representing a random number of (random) object states, an issue that has been largely ignored in the tracking literature until recently. Although a satisfactory foundation for multiple object filtering has been provided by random set theory, in this ear ....Stochastic Geometry for Multi-sensor Data Fusion System. The aim of this project is to develop efficient algorithms for tracking and sensor management in a multi-sensor multi-target environment. Finite random set theory provides a natural way of representing a random number of (random) object states, an issue that has been largely ignored in the tracking literature until recently. Although a satisfactory foundation for multiple object filtering has been provided by random set theory, in this early stage no algorithm capable of tracking many targets has emerged from this framework. We are confident that efficient algorithms can be developed by exploiting the insights and mathematical tools of stochastic geometryRead moreRead less