caa a22 4500 477034349 CHVBK 20180405111301.0 cr unu---uuuuu 170330e19960401xx s 000 0 eng 10.1007/BF00417789 doi (NATIONALLICENCE)springer-10.1007/BF00417789 Kirke A. Neurodynamics Research Group, School of Computing, University of Plymouth, PL4 8AA, Plymouth, UK aut A short term memory for Neural Networds which allows recognition and reproduction of complex sequences of integers with the minimum number of weights [Elektronische Daten] [A. Kirke] An artificial short term memory, the binary kernel function, is presented to facilitate the learning of complex sequences of integers by Neural Networks, requiring far fewer weights than are usually needed. This is achieved by using only a single weight to encode repeat occurrences of an integer in a sequence. The coding used allows a complex sequence to be learned in only one presentation. The kernel's exponential complexity growth is overcome with hierarchical architectures which chunk the sequences to be learnt. Architectures are introduced for recognition and reproduction of complex sequences. Kluwer Academic Publishers, 1996 complex sequence learning nationallicence kernel function nationallicence neural network nationallicence short term memory nationallicence Neural Processing Letters Kluwer Academic Publishers; http://www.wkap.nl 3/1(1996-04-01), 49-54 1370-4621 3:1<49 1996 3 11063 https://doi.org/10.1007/BF00417789 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/BF00417789 text/html Onlinezugriff via DOI NATIONALLICENCE 100 1- Kirke A. Neurodynamics Research Group, School of Computing, University of Plymouth, PL4 8AA, Plymouth, UK aut NATIONALLICENCE 773 0- Neural Processing Letters Kluwer Academic Publishers; http://www.wkap.nl 3/1(1996-04-01), 49-54 1370-4621 3:1<49 1996 3 11063 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer