A hybrid ART-GRNN online learning neural network with a ε-insensitive loss function

In this brief, a new neural network model called generalized adaptive resonance theory (GART) is introduced. GART is a hybrid model that comprises a modified Gaussian adaptive resonance theory (MGA) and the generalized regression neural network (GRNN). It is an enhanced version of the GRNN, which preserves the online learning properties of adaptive resonance theory (ART). A series of empirical studies to assess the effectiveness of GART in classification, regression, and time series prediction tasks is conducted. The results demonstrate that GART is able to produce good performances as compared with those of other methods, including the online sequential extreme learning machine (OSELM) and sequential learning radial basis function (RBF) neural network models.

A modified micro genetic algorithm for undertaking multi-objective optimization problems

In this paper, a Modified micro Genetic Algorithm (MmGA) is proposed for undertaking Multi-objective Optimization Problems (MOPs). An NSGA-II inspired elitism strategy and a population initialization strategy are embedded into the traditional micro Genetic Algorithm (mGA) to form the proposed MmGA. The main aim of the MmGA is to improve its convergence rate towards the pareto optimal solutions. To evaluate the effectiveness of the MmGA, two experiments using the Kursawe test function in MOPs are conducted, and the results are compared with those from other approaches using a multi-objective evolutionary algorithm indicator, i.e. the Generational Distance (GD). The outcomes positively demonstrate that the MmGA is able to provide useful solutions with improved GD measures for tackling MOPs.

Coathanger : Finalist in the 2014 Bowness Prize

In the attempt to understand how the camera works I built a camera obscura and discovered that photography exists without us. That nature produces pinholes of light that form images came as a revelation. This spawned a new way of exploring the body in motion through photography. Guided by instinctual body memory of light and space I impose rules on how and when I shoot. In this series I ‘performed’ states of motion by combining elements together - a pas de trois of gravity, water and body mass caught in a flash, the action commonly known as ‘bombing’. I continue to ‘choreograph’ the moment in photoshop just like dance notation as if it could be read and repeated.

Bowness Prize Finalists Exhibition

A group exhbition of 48 finalists for the 2014 Bowness Photography Prize