Generalisation capabilities of a distributed neural classifier
نویسندگان
چکیده
This article describes a new approach to the automated construction of a distributed neural classifier. The methodology is based upon supervised hierarchical clustering which enables one to determine reliable regions in the representation space. The proposed methodology proceeds by associating each of these regions with a Multi-Layer Perceptron (MLP). Each MLP has to recognise elements inside its region, while rejecting all others. Experimental results for a real problem (handwritten digit recognition) reveal an interesting generalisation behaviour of the distributed classifier in comparison to the knearest neighbour algorithm as well as a single MLP.
منابع مشابه
On Generalisation of Machine Learning with Neural-Evolutionary Computations
Generalisation is a non-trivial problem in machine learning and more so with neural networks which have the capabilities of inducing varying degrees of freedom. It is influenced by many factors in network design, such as network size, initial conditions, learning rate, weight decay factor, pruning algorithms, and many more. In spite of continuous research efforts we could not arrive at a practi...
متن کاملGenerating-shrinking algorithm for learning arbitrary classification
This paper proposes a novel generating-shrinking algorithm, which builds and then shrinks a three-layer feed-forward neural network to achieve arbitrary classification in n-dimensional Euclidean space. The algorithm offers guaranteed convergence to a 100% correct classification rate on training patterns. Decision regions resulting from the algorithm are analytically described, so the generalisa...
متن کاملUsing Feature Selection Techniques to Produce Smaller Neural Networks with Better Generalisation Capabilities
The issue of feature selection is of considerable importance, particularly where artificial neural networks are used, as the size of the network is directly related to the number of input sources. Despite the fact that artificial neural networks have been applied to solve many problems in different fields, and found to be superior to conventional statistical classifiers, they have a major drawb...
متن کاملIn-Situ Learning in Multi-net Systems
Multiple classifier systems based on neural networks can give improved generalisation performance as compared with single classifier systems. We examine collaboration in multi-net systems through in-situ learning, exploring how generalisation can be improved through the simultaneous learning in networks and their combination. We present two in-situ trained systems; first, one based upon the sim...
متن کاملA DWT and SVM based method for rolling element bearing fault diagnosis and its comparison with Artificial Neural Networks
A classification technique using Support Vector Machine (SVM) classifier for detection of rolling element bearing fault is presented here. The SVM was fed from features that were extracted from of vibration signals obtained from experimental setup consisting of rotating driveline that was mounted on rolling element bearings which were run in normal and with artificially faults induced conditio...
متن کامل