caa a22 4500 477072836 CHVBK 20180405111431.0 cr unu---uuuuu 170330e19960301xx s 000 0 eng 10.1007/BF01413869 doi (NATIONALLICENCE)springer-10.1007/BF01413869 Mackenzie M. Information Technology Department, Christchurch College, North Holmes Road, Canterbury, Kent, UK aut Enhancements to the dynamic self-organising neural network [Elektronische Daten] [M. Mackenzie] Class Directed Unsupervised Learning (CDUL) is a dynamic self-organising network which has been shown to overcome many of the problems associated with unsupervised learning, thereby yielding performance characteristics superior to similar networks such as counter-propagation and LVQ. In this paper, the CDUL algorithm is developed further, to a point where the original two-phase learning process is combined into a single system of dynamic parameter variation; a training cycle that can then be terminated automatically at a point of zero error over the training set. The ability to improve training times using a FastCDUL algorithm is also explored. The new algorithm, CDUL2, is subsequently applied to the benchmark problem of mine detection given sonar data, and shown to outperform both backpropagation and LVQ in terms of training speed and recall performance. Finally, a measure of computational cost is estimated for both CDUL2 and LVQ training periods, reinforcing the suggested efficiency of CDUL2 over its counterparts. Springer-Verlag London Limited, 1996 Classification nationallicence Competitive network nationallicence Computational cost nationallicence Dynamic network architecture nationallicence Feature space nationallicence Kohonen nodes nationallicence Mine detection nationallicence Neural Computing & Applications Springer-Verlag 4/1(1996-03-01), 44-57 0941-0643 4:1<44 1996 4 521 https://doi.org/10.1007/BF01413869 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/BF01413869 text/html Onlinezugriff via DOI NATIONALLICENCE 100 1- Mackenzie M. Information Technology Department, Christchurch College, North Holmes Road, Canterbury, Kent, UK aut NATIONALLICENCE 773 0- Neural Computing & Applications Springer-Verlag 4/1(1996-03-01), 44-57 0941-0643 4:1<44 1996 4 521 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer