Proceedings of the International Joint Conference on Neural Networks, 2003.
Published 1 January 2003
Citations1,673
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
Abstract
In this paper we establish a simple hybrid cognition system which is based on neural netwoks and fuzzy decision theory.For the purpose of analyzing the trends of stock market, we expect that the system can reflect the dynamical character or chsot ic performance of a trading stock market. The whole procedure of the system include: data preprocessing, neural network classif icat ion, fuzzy decision and forecast ing,
Keywords
Computer ScienceDecision Sciences
Fixed-point roundoff error analysis of large feedforward neural networks
5 Citations2005Hyunjun Choi, Wayne Burleson +1 more
Output error expressions for a large feedforward neural net are presented, which are based on statistical error analysis and indicate that for equal wordlengths, multiplier roundoff errors exceed weight quantization errors by about an order of magnitude.
Synthetic face expressions generated by self organizing maps
2 Citations2005Stefan Jockusch, Helge Ritter
It is shown that topology conserving maps and their extension to local linear mapping (LLM) networks allow a very efficient representation of critical face segments and that they are able to produce a sequence of realistic expressions in real time.
The general purpose neurocomputer "Hercules"
1 Citations2005L.V. Grachev, E.J. Kirsanov
The term "neurocomputers" and their classification are discussed and the GPNC "Hercules" is described, which has the accelerators for neural basis operations.