Matches in SemOpenAlex for { <https://semopenalex.org/work/W2297367780> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W2297367780 abstract "The classical Artificial Neural Network (ANN) has a complete feed-forward topology, which is useful in some contexts but is not suited to applications where both the inputs and targets have very low signal-to-noise ratios, e.g. financial forecasting problems. This is because this topology implies a very large number of parameters (i.e. the model contains too many degrees of freedom) that leads to over fitting of both signals and noise. This results in the ANN having very good in-sample performance on the data used for its training but poor performance outof-sample for forecasting.The main contribution of my research is to develop a new heuristic method called “ANN reduction” for optimising the topological structure of a feed-forward ANN in order to improve its out-of-sample performance (using an RMS measure). The research concentrated on the topological optimization of the graph representing an ANN, which reduces the effective degrees of freedom of the ANN whilst still maintaining its feed-forward (but incomplete) topology. Such reductions in the number of parameters have been attempted before in the literature, but our procedure is of a different (graph theoretic) nature and (in extremis) optimal for small-size ANNs.Two applications of the ANN reduction are also implemented and programmed for empirical simulations. For this purpose, two datasets generated from deterministic functions and three datasets derived from foreign exchange market prices are used for evaluating the ANN reduction applications. These applications generate new ANN topologies with some clear performance advantages over those obtained by the best complete ANNs, improving the generalization (out-of-sample) performance by up to 27.6% compared to the complete ANN on thefunction generated datasets and up to 14.1% on the financial forecasting problem for the FX data." @default.
- W2297367780 created "2016-06-24" @default.
- W2297367780 creator A5000132939 @default.
- W2297367780 date "2015-04-01" @default.
- W2297367780 modified "2023-09-26" @default.
- W2297367780 title "Topological optimisation of artificial neural networks for financial asset forecasting" @default.
- W2297367780 hasPublicationYear "2015" @default.
- W2297367780 type Work @default.
- W2297367780 sameAs 2297367780 @default.
- W2297367780 citedByCount "0" @default.
- W2297367780 crossrefType "dissertation" @default.
- W2297367780 hasAuthorship W2297367780A5000132939 @default.
- W2297367780 hasConcept C111335779 @default.
- W2297367780 hasConcept C111919701 @default.
- W2297367780 hasConcept C114614502 @default.
- W2297367780 hasConcept C126255220 @default.
- W2297367780 hasConcept C132525143 @default.
- W2297367780 hasConcept C154945302 @default.
- W2297367780 hasConcept C173801870 @default.
- W2297367780 hasConcept C184720557 @default.
- W2297367780 hasConcept C185592680 @default.
- W2297367780 hasConcept C198531522 @default.
- W2297367780 hasConcept C199845137 @default.
- W2297367780 hasConcept C2524010 @default.
- W2297367780 hasConcept C33923547 @default.
- W2297367780 hasConcept C41008148 @default.
- W2297367780 hasConcept C43617362 @default.
- W2297367780 hasConcept C50644808 @default.
- W2297367780 hasConcept C80444323 @default.
- W2297367780 hasConceptScore W2297367780C111335779 @default.
- W2297367780 hasConceptScore W2297367780C111919701 @default.
- W2297367780 hasConceptScore W2297367780C114614502 @default.
- W2297367780 hasConceptScore W2297367780C126255220 @default.
- W2297367780 hasConceptScore W2297367780C132525143 @default.
- W2297367780 hasConceptScore W2297367780C154945302 @default.
- W2297367780 hasConceptScore W2297367780C173801870 @default.
- W2297367780 hasConceptScore W2297367780C184720557 @default.
- W2297367780 hasConceptScore W2297367780C185592680 @default.
- W2297367780 hasConceptScore W2297367780C198531522 @default.
- W2297367780 hasConceptScore W2297367780C199845137 @default.
- W2297367780 hasConceptScore W2297367780C2524010 @default.
- W2297367780 hasConceptScore W2297367780C33923547 @default.
- W2297367780 hasConceptScore W2297367780C41008148 @default.
- W2297367780 hasConceptScore W2297367780C43617362 @default.
- W2297367780 hasConceptScore W2297367780C50644808 @default.
- W2297367780 hasConceptScore W2297367780C80444323 @default.
- W2297367780 hasLocation W22973677801 @default.
- W2297367780 hasOpenAccess W2297367780 @default.
- W2297367780 hasPrimaryLocation W22973677801 @default.
- W2297367780 hasRelatedWork W1866664556 @default.
- W2297367780 hasRelatedWork W1987345571 @default.
- W2297367780 hasRelatedWork W2030888282 @default.
- W2297367780 hasRelatedWork W2031155980 @default.
- W2297367780 hasRelatedWork W2034490806 @default.
- W2297367780 hasRelatedWork W2068499891 @default.
- W2297367780 hasRelatedWork W2119367820 @default.
- W2297367780 hasRelatedWork W2125603750 @default.
- W2297367780 hasRelatedWork W2144883937 @default.
- W2297367780 hasRelatedWork W2145646455 @default.
- W2297367780 hasRelatedWork W2146443196 @default.
- W2297367780 hasRelatedWork W2279552445 @default.
- W2297367780 hasRelatedWork W2293444041 @default.
- W2297367780 hasRelatedWork W2347115965 @default.
- W2297367780 hasRelatedWork W2761929139 @default.
- W2297367780 hasRelatedWork W3125022948 @default.
- W2297367780 hasRelatedWork W45452093 @default.
- W2297367780 hasRelatedWork W1582964342 @default.
- W2297367780 hasRelatedWork W2310231560 @default.
- W2297367780 hasRelatedWork W2524006690 @default.
- W2297367780 isParatext "false" @default.
- W2297367780 isRetracted "false" @default.
- W2297367780 magId "2297367780" @default.
- W2297367780 workType "dissertation" @default.