Matches in SemOpenAlex for { <https://semopenalex.org/work/W2141703670> ?p ?o ?g. }
- W2141703670 endingPage "183" @default.
- W2141703670 startingPage "161" @default.
- W2141703670 abstract "Financial forecasting is an example of a signal processing problem which is challenging due to small sample sizes, high noise, non-stationarity, and non-linearity. Neural networks have been very successful in a number of signal processing applications. We discuss fundamental limitations and inherent difficulties when using neural networks for the processing of high noise, small sample size signals. We introduce a new intelligent signal processing method which addresses the difficulties. The method proposed uses conversion into a symbolic representation with a self-organizing map, and grammatical inference with recurrent neural networks. We apply the method to the prediction of daily foreign exchange rates, addressing difficulties with non-stationarity, overfitting, and unequal a priori class probabilities, and we find significant predictability in comprehensive experiments covering 5 different foreign exchange rates. The method correctly predicts the directionof change for the next day with an error rate of 47.1%. The error rate reduces to around 40% when rejecting examples where the system has low confidence in its prediction. We show that the symbolic representation aids the extraction of symbolic knowledge from the trained recurrent neural networks in the form of deterministic finite state automata. These automata explain the operation of the system and are often relatively simple. Automata rules related to well known behavior such as tr end following and mean reversal are extracted." @default.
- W2141703670 created "2016-06-24" @default.
- W2141703670 creator A5001294898 @default.
- W2141703670 creator A5043733219 @default.
- W2141703670 creator A5077581403 @default.
- W2141703670 date "2001-01-01" @default.
- W2141703670 modified "2023-09-30" @default.
- W2141703670 cites W1508395088 @default.
- W2141703670 cites W1508947067 @default.
- W2141703670 cites W1518194904 @default.
- W2141703670 cites W1527338945 @default.
- W2141703670 cites W1528056001 @default.
- W2141703670 cites W1533986854 @default.
- W2141703670 cites W1536929369 @default.
- W2141703670 cites W1549386224 @default.
- W2141703670 cites W1572697648 @default.
- W2141703670 cites W1575881144 @default.
- W2141703670 cites W1588861010 @default.
- W2141703670 cites W1679913846 @default.
- W2141703670 cites W1724577157 @default.
- W2141703670 cites W1797539709 @default.
- W2141703670 cites W1966728884 @default.
- W2141703670 cites W1982370770 @default.
- W2141703670 cites W1989574962 @default.
- W2141703670 cites W2002089154 @default.
- W2141703670 cites W2015140204 @default.
- W2141703670 cites W2017059355 @default.
- W2141703670 cites W2036677213 @default.
- W2141703670 cites W2053987251 @default.
- W2141703670 cites W2054599015 @default.
- W2141703670 cites W2067619114 @default.
- W2141703670 cites W2068036649 @default.
- W2141703670 cites W2087946919 @default.
- W2141703670 cites W2094558429 @default.
- W2141703670 cites W2103116581 @default.
- W2141703670 cites W2110450942 @default.
- W2141703670 cites W2112036221 @default.
- W2141703670 cites W2115027220 @default.
- W2141703670 cites W2115072676 @default.
- W2141703670 cites W2116664051 @default.
- W2141703670 cites W2120339295 @default.
- W2141703670 cites W2121553911 @default.
- W2141703670 cites W2123457147 @default.
- W2141703670 cites W2124776405 @default.
- W2141703670 cites W2126685080 @default.
- W2141703670 cites W2131773668 @default.
- W2141703670 cites W2135691157 @default.
- W2141703670 cites W2141278204 @default.
- W2141703670 cites W2152080463 @default.
- W2141703670 cites W2155677642 @default.
- W2141703670 cites W2156960699 @default.
- W2141703670 cites W2158663270 @default.
- W2141703670 cites W2161086430 @default.
- W2141703670 cites W2166116275 @default.
- W2141703670 cites W2167615167 @default.
- W2141703670 cites W2170702935 @default.
- W2141703670 cites W2270864342 @default.
- W2141703670 cites W2337958348 @default.
- W2141703670 cites W2896916590 @default.
- W2141703670 cites W3036383388 @default.
- W2141703670 cites W3124941243 @default.
- W2141703670 cites W3143451078 @default.
- W2141703670 cites W3151666377 @default.
- W2141703670 cites W33670048 @default.
- W2141703670 cites W421997344 @default.
- W2141703670 cites W56903235 @default.
- W2141703670 cites W2275214226 @default.
- W2141703670 cites W913319393 @default.
- W2141703670 doi "https://doi.org/10.1023/a:1010884214864" @default.
- W2141703670 hasPublicationYear "2001" @default.
- W2141703670 type Work @default.
- W2141703670 sameAs 2141703670 @default.
- W2141703670 citedByCount "331" @default.
- W2141703670 countsByYear W21417036702012 @default.
- W2141703670 countsByYear W21417036702013 @default.
- W2141703670 countsByYear W21417036702014 @default.
- W2141703670 countsByYear W21417036702015 @default.
- W2141703670 countsByYear W21417036702016 @default.
- W2141703670 countsByYear W21417036702017 @default.
- W2141703670 countsByYear W21417036702018 @default.
- W2141703670 countsByYear W21417036702019 @default.
- W2141703670 countsByYear W21417036702020 @default.
- W2141703670 countsByYear W21417036702021 @default.
- W2141703670 countsByYear W21417036702022 @default.
- W2141703670 countsByYear W21417036702023 @default.
- W2141703670 crossrefType "journal-article" @default.
- W2141703670 hasAuthorship W2141703670A5001294898 @default.
- W2141703670 hasAuthorship W2141703670A5043733219 @default.
- W2141703670 hasAuthorship W2141703670A5077581403 @default.
- W2141703670 hasBestOaLocation W21417036701 @default.
- W2141703670 hasConcept C104267543 @default.
- W2141703670 hasConcept C105795698 @default.
- W2141703670 hasConcept C112505250 @default.
- W2141703670 hasConcept C11413529 @default.
- W2141703670 hasConcept C115961682 @default.
- W2141703670 hasConcept C119857082 @default.
- W2141703670 hasConcept C153180895 @default.
- W2141703670 hasConcept C154945302 @default.