Global tradeoffs for aerodynamic design of Supersonic Transport (SST) have been investigated by Multi-Objective Evolutionary Algorithms (MOEAs). The objectives are to reduce both drag and sonic boom to make next-generation SST more feasible. Adaptive Range MultiObjective Genetic Algorithms (ARMOGAs) are utilised for the efficient search. The trade-offs are analysed by Self-Organising Map (SOM),...

In this paper the capability of using self-organising neural maps (SOM) as music style classifiers of musical fragments is studied. From MIDI files, the monophonic melody track is extracted and cut into fragments of equal length. From these sequences, melodic, harmonic, and rhythmic numerical descriptors are computed and presented to the SOM. Their performance is analysed in terms of separabili...

We present a method based on the non-linear behaviour of neural network for the identification of the early-type population in the cores of galaxy clusters. A Kohonen Self Organising Map applied on a three-colour photometric catalogue of objects enabled us to select in each passband the elliptical galaxies. We measured in this way the luminosity function of the E/S0 galaxies selected in this wa...

In this paper, we apply the combination method of bagging which has been developed in the context of supervised learning of classifiers and regressors to the unsupervised artificial neural network known as the Self Organising Map. We show that various initialisation techniques can be used to create maps which are comparable by humans by eye. We then use a semi-supervised version of the SOM to c...

The measurement of distance is one of the key steps in the unsupervised learning process, as it is through these distance measurements that patterns and correlations are discovered. We examined the characteristics of both non-Euclidean norms and data normalisation within the unsupervised learning environment. We empirically assessed the performance of the K-means, Neural Gas, Growing Neural Gas...

This paper presents a technique, the Quantum Web Field, designed to give an ambient visualisation of the current activity on a web site. It uses the paths of past visitors to the site and a self-organising map to build a diffuse 'probabilistic' mapping of pages to cells in a 2D matrix, where highly traversed page-links tend to be closer to each other. The paths of current visitors appear as int...

A topographic mapping of angular whisker deflections has recently been discovered in the barrel cortex of rats (Andermann & Moore, 2006). Characteristics of this map suggest that it could emerge in post-natal development, through self-organisation under a Hebbian learning regime. This hypothesis was implemented in a self-organising computational model, from which a remarkably similar mapping em...

The paper describes how neural networks may be used to segment and label objects in images. A self-organising feature map is used for the segmentation phase, and we quantify the quality of the segmentations produced as well as the contribution made by colour and texture features. A multi-layer perception is trained to label the regions produced by the segmentation process. It is shown that 91.1...

We study the behaviour of the Ben-Yishai hypercolumn model 2] under presentation of oriented stimuli, having extended this model by including plastic aaerent (LGN to cortex) connections. We nd that Hebbian plasticity creates a self-organising map and show that constraining or modifying the standard Hebb rule in a particular way will lead to a contrast-insensitive tuning width, thus giving an ex...

In this approach to named entity recognition, a recurrent neural network, known as Long Short-Term Memory, is applied. The network is trained to perform 2 passes on each sentence, outputting its decisions on the second pass. The first pass is used to acquire information for disambiguation during the second pass. SARDNET, a self-organising map for sequences is used to generate representations fo...