caa a22 4500 477072852 CHVBK 20180405111431.0 cr unu---uuuuu 170330e19960301xx s 000 0 eng 10.1007/BF01413865 doi (NATIONALLICENCE)springer-10.1007/BF01413865 A Multi-Output-Layer Perceptron [Elektronische Daten] [F. Owens, G. Zheng, D. Irvine] This paper investigates the possibility of improving the classification capability of single-layer and multilayer perceptrons by incorporating additional output layers. This Multi-Output-Layer Perceptron (MOLP) is a new type of constructive network, though the emphasis is on improving pattern separability rather than network efficiency. The MOLP is trained using the standard back-propagation (BP) algorithm. The studies are concentrated on realizations of arbitrary functions which map from an x-dimensional input MOLP, all problems existing in an original n-dimensional space in the hidden layer are transformed to a higher (n +1)-dimensional space, so that the possibility of linear separability is increased. Experimental investigations show that the classification ability of the MOLP is superior to that of an equivalent MLP. In general, this performance increase can be achieved with shorter training times and simpler network architectures. Springer-Verlag London Limited, 1996 Constructive algorithms nationallicence Multi-outputlayer perceptrons nationallicence Neural networks nationallicence Owens F. Northern Ireland Bioengineering Centre, School of Electrical and Mechanical Engineering, Faculty of Engineering, University of Ulster at Jordanstown, Shore Road, BT37 0QB, Newtownabbey, Co. Antrim, Northern Ireland aut Zheng G. Northern Ireland Bioengineering Centre, School of Electrical and Mechanical Engineering, Faculty of Engineering, University of Ulster at Jordanstown, Shore Road, BT37 0QB, Newtownabbey, Co. Antrim, Northern Ireland aut Irvine D. Northern Ireland Bioengineering Centre, School of Electrical and Mechanical Engineering, Faculty of Engineering, University of Ulster at Jordanstown, Shore Road, BT37 0QB, Newtownabbey, Co. Antrim, Northern Ireland aut Neural Computing & Applications Springer-Verlag 4/1(1996-03-01), 10-20 0941-0643 4:1<10 1996 4 521 https://doi.org/10.1007/BF01413865 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/BF01413865 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Owens F. Northern Ireland Bioengineering Centre, School of Electrical and Mechanical Engineering, Faculty of Engineering, University of Ulster at Jordanstown, Shore Road, BT37 0QB, Newtownabbey, Co. Antrim, Northern Ireland aut NATIONALLICENCE 700 1- Zheng G. Northern Ireland Bioengineering Centre, School of Electrical and Mechanical Engineering, Faculty of Engineering, University of Ulster at Jordanstown, Shore Road, BT37 0QB, Newtownabbey, Co. Antrim, Northern Ireland aut NATIONALLICENCE 700 1- Irvine D. Northern Ireland Bioengineering Centre, School of Electrical and Mechanical Engineering, Faculty of Engineering, University of Ulster at Jordanstown, Shore Road, BT37 0QB, Newtownabbey, Co. Antrim, Northern Ireland aut NATIONALLICENCE 773 0- Neural Computing & Applications Springer-Verlag 4/1(1996-03-01), 10-20 0941-0643 4:1<10 1996 4 521 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer