Stefan Wermter

Learn More
Recently there has been a lot of interest in the extrac tion of symbolic rules from neural networks The work described in this paper is concerned with an evaluation and comparison of the accuracy and complexity of sym bolic rules extracted from radial basis function networks and multi layer perceptrons Here we examine the abil ity of rule extraction(More)
This paper examines the performance of seven neural network architectures in classifying and detecting novel events contained within data collected from turbine sensors. Several different multi-layer perceptrons were built and trained using back propagation, conjugate gradient and Quasi-Newton training algorithms. In addition, Linear networks, Radial Basis(More)
The Kohonen self-organising feature map (SOM) has several important properties that can be used within the data mining/knowledge discovery and exploratory data analysis process. A key characteristic of the SOM is its topology preserving ability to map a multi-dimensional input into a two-dimensional form. This feature is used for classification and(More)
By frame of reference transformations, an input variable in one coordinate system is transformed into an output variable in a different coordinate system depending on another input variable. If the variables are represented as neural population codes, then a sigma–pi network is a natural way of coding this transformation. By multiplying two inputs it(More)
Interaural Time Difference (ITD) is used in the mammalian auditory system to compute the angle of incidence of an acoustic sound-source on the horizontal plane. This paper describes how ITD can be incorporated into a robotic acoustic tracking system to enable the robot to locate and orient towards sound-sources within its environment. We describe a system(More)
Document clustering is text processing that groups documents with similar concepts. It's usually considered an unsupervised learning approach because there's no teacher to guide the training process, and topical information is often assumed to be unavailable. A guided approach to document clustering that integrates linguistic top-down knowledge from WordNet(More)
We present a solution for robotic docking, i.e. approach of a robot toward a table so that it can grasp an object. One constraint is that our PeopleBot robot has a short non-extendable gripper and wide ‘shoulders’. Therefore, it must approach the table at a perpendicular angle so that the gripper can reach over it. Another constraint is the use of vision to(More)
We have applied several dimensionality reduction techniques to data modelling using neural network architectures for classification using a number of data sets. The reduction methods considered include both linear and non linear forms of principal components analysis, genetic algorithms and sensitivity analysis. The results of each were used as inputs to(More)
Radial basis neural (RBF) networks provide an excellent solution to many pattern recognition and classi cation problems. However, RBF networks are also a local representation technique that enables the easy conversion of the hidden units into symbolic rules. This paper examines rules extracted from RBF networks. We use the iris ower classication task and a(More)