Matches in SemOpenAlex for { <https://semopenalex.org/work/W414207107> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W414207107 abstract "Title of Thesis: NEW NEURAL NETWORK DESIGN FOR APPROXIMATE DYNAMIC PROGRAMMING AND OPTIMAL MULTIUSER DETECTION Degree candidate: Xiaozhong Pang Degree and year: Master of Science, 1997 Thesis directed by: Professor John S. Baras Department of Electrical Engineering and Institute for Systems Research In this thesis we demonstrate that a new neural network design can be used to solve a class of di cult function approximation problems which are crucial to the eld of approximate dynamic programming(ADP). Although conventional neural networks have been proven to approximate smooth functions very well, the use of ADP for problems of intelligent control or planning requires the approximation of functions which are not so smooth. As an example, this thesis studies the problem of approximating the J function of dynamic programming applied to the task of navigating mazes, in general, without the need to learn each individual maze. Conventional neural networks, like multi-layer perceptrons(MLPs), cannot learn this task. But a new type of neural networks, simultaneous recurrent networks(SRNs), can accomplish the required learning as demonstrated by successful initial tests. In this thesis we investigate also the ability of recurrent neural networks to approximate MLPs and vice versa. Moreover, we present a comparison between using SRNs and MLPs to implement the optimal CDMA multiuser detector (OMD). This example is intended to demonstrate that SRNs can provide fast suboptimal solutions to hard combinatorial optimization problems, and achieve better bit-error-rate (BER) performance than MLPs. NEW NEURAL NETWORK DESIGN FOR APPROXIMATE DYNAMIC PROGRAMMING AND OPTIMAL MULTIUSER DETECTION" @default.
- W414207107 created "2016-06-24" @default.
- W414207107 creator A5054500913 @default.
- W414207107 date "1998-01-01" @default.
- W414207107 modified "2023-09-27" @default.
- W414207107 title "New Neural Network Design for Approximate Dynamic Programming and Optimal Multiuser Detection" @default.
- W414207107 cites W1487148666 @default.
- W414207107 cites W1511586053 @default.
- W414207107 cites W1566309885 @default.
- W414207107 cites W1600202182 @default.
- W414207107 cites W1881179843 @default.
- W414207107 cites W1907796993 @default.
- W414207107 cites W1971129545 @default.
- W414207107 cites W2017571220 @default.
- W414207107 cites W2020571005 @default.
- W414207107 cites W2028145673 @default.
- W414207107 cites W2059786462 @default.
- W414207107 cites W2112246162 @default.
- W414207107 cites W2119025246 @default.
- W414207107 cites W2152343444 @default.
- W414207107 cites W2152559190 @default.
- W414207107 cites W2160779252 @default.
- W414207107 cites W2160819228 @default.
- W414207107 cites W2172733085 @default.
- W414207107 cites W2766736793 @default.
- W414207107 cites W3121926921 @default.
- W414207107 cites W3145436600 @default.
- W414207107 cites W355721981 @default.
- W414207107 hasPublicationYear "1998" @default.
- W414207107 type Work @default.
- W414207107 sameAs 414207107 @default.
- W414207107 citedByCount "0" @default.
- W414207107 crossrefType "dissertation" @default.
- W414207107 hasAuthorship W414207107A5054500913 @default.
- W414207107 hasConcept C108583219 @default.
- W414207107 hasConcept C11413529 @default.
- W414207107 hasConcept C126255220 @default.
- W414207107 hasConcept C14036430 @default.
- W414207107 hasConcept C147168706 @default.
- W414207107 hasConcept C154945302 @default.
- W414207107 hasConcept C2777104032 @default.
- W414207107 hasConcept C33923547 @default.
- W414207107 hasConcept C37404715 @default.
- W414207107 hasConcept C41008148 @default.
- W414207107 hasConcept C50644808 @default.
- W414207107 hasConcept C60908668 @default.
- W414207107 hasConcept C76155785 @default.
- W414207107 hasConcept C78458016 @default.
- W414207107 hasConcept C86803240 @default.
- W414207107 hasConcept C91873725 @default.
- W414207107 hasConcept C94915269 @default.
- W414207107 hasConceptScore W414207107C108583219 @default.
- W414207107 hasConceptScore W414207107C11413529 @default.
- W414207107 hasConceptScore W414207107C126255220 @default.
- W414207107 hasConceptScore W414207107C14036430 @default.
- W414207107 hasConceptScore W414207107C147168706 @default.
- W414207107 hasConceptScore W414207107C154945302 @default.
- W414207107 hasConceptScore W414207107C2777104032 @default.
- W414207107 hasConceptScore W414207107C33923547 @default.
- W414207107 hasConceptScore W414207107C37404715 @default.
- W414207107 hasConceptScore W414207107C41008148 @default.
- W414207107 hasConceptScore W414207107C50644808 @default.
- W414207107 hasConceptScore W414207107C60908668 @default.
- W414207107 hasConceptScore W414207107C76155785 @default.
- W414207107 hasConceptScore W414207107C78458016 @default.
- W414207107 hasConceptScore W414207107C86803240 @default.
- W414207107 hasConceptScore W414207107C91873725 @default.
- W414207107 hasConceptScore W414207107C94915269 @default.
- W414207107 hasLocation W4142071071 @default.
- W414207107 hasOpenAccess W414207107 @default.
- W414207107 hasPrimaryLocation W4142071071 @default.
- W414207107 hasRelatedWork W1564299664 @default.
- W414207107 hasRelatedWork W1570584848 @default.
- W414207107 hasRelatedWork W1820595713 @default.
- W414207107 hasRelatedWork W1861060154 @default.
- W414207107 hasRelatedWork W1981980472 @default.
- W414207107 hasRelatedWork W2051313871 @default.
- W414207107 hasRelatedWork W2080355190 @default.
- W414207107 hasRelatedWork W2097082695 @default.
- W414207107 hasRelatedWork W2122297221 @default.
- W414207107 hasRelatedWork W2272487030 @default.
- W414207107 hasRelatedWork W2497655912 @default.
- W414207107 hasRelatedWork W2609698191 @default.
- W414207107 hasRelatedWork W265797962 @default.
- W414207107 hasRelatedWork W2800023535 @default.
- W414207107 hasRelatedWork W2962735857 @default.
- W414207107 hasRelatedWork W3048171402 @default.
- W414207107 hasRelatedWork W3148449846 @default.
- W414207107 hasRelatedWork W3171379052 @default.
- W414207107 hasRelatedWork W3204858378 @default.
- W414207107 hasRelatedWork W2181948416 @default.
- W414207107 isParatext "false" @default.
- W414207107 isRetracted "false" @default.
- W414207107 magId "414207107" @default.
- W414207107 workType "dissertation" @default.