caa a22 4500 388091509 CHVBK 20180307125253.0 cr unu---uuuuu 161130e199902 xx s 000 0 eng 10.1017/S0004972700032676 doi S0004972700032676 pii (NATIONALLICENCE)cambridge-10.1017/S0004972700032676 Extension of localised approximation by neural networks [Elektronische Daten] We prove generalised results for localised approximation by generalised translation networks. We also show the relationship between the minimum number of neurons in the generalised translation networks with one hidden layer and the desired accuracy where the target functions are in a subset V1, p ([−1, 1]s) of the Sobolev space W1, p([−1, 1]s). Copyright © Australian Mathematical Society 1999 Hahm Nahmwoo Institute of Natural Sciences, Kyung Hee University, Yongin, Kyunggi 449-701, Korea e-mail: nhahm@lion.inchon.ac.kr Hong Bum Il Department of Mathematics, Kyung Hee Univeristy, Yongin, Kyunggi 449-701, Korea e-mail: bihong@nms.kyunghee.ac.kr Bulletin of the Australian Mathematical Society Cambridge University Press 59/1(1999-02), 121-131 0004-9727 59:1<121 1999 59 BAZ https://doi.org/10.1017/S0004972700032676 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1017/S0004972700032676 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Hahm Nahmwoo Institute of Natural Sciences, Kyung Hee University, Yongin, Kyunggi 449-701, Korea e-mail: nhahm@lion.inchon.ac.kr NATIONALLICENCE 700 1- Hong Bum Il Department of Mathematics, Kyung Hee Univeristy, Yongin, Kyunggi 449-701, Korea e-mail: bihong@nms.kyunghee.ac.kr NATIONALLICENCE 773 0- Bulletin of the Australian Mathematical Society Cambridge University Press 59/1(1999-02), 121-131 0004-9727 59:1<121 1999 59 BAZ CC0 http://creativecommons.org/publicdomain/zero/1.0 nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-cambridge