Results 1 
8 of
8
Hidden Patterns in Combined and Adaptive Knowledge Networks
 International Journal of Approximate Reasoning
, 1988
"... Uncertain causal knowledge is stored in fuzzy cognitive maps (FCMs). FCMs are fuzzy signed digraphs with feedback. The sign (+ or) of FCM edges indicates causal increase or causal decrease. The fuzzy degree of causality is indicated by a number in [ 1, 1]. FCMs learn by modifying their causal conn ..."
Abstract

Cited by 46 (2 self)
 Add to MetaCart
(Show Context)
Uncertain causal knowledge is stored in fuzzy cognitive maps (FCMs). FCMs are fuzzy signed digraphs with feedback. The sign (+ or) of FCM edges indicates causal increase or causal decrease. The fuzzy degree of causality is indicated by a number in [ 1, 1]. FCMs learn by modifying their causal connections in sign and magnitude, structurally analogous to the way in which neural networks learn. An appropriate causal learning law for inductively inferring FCMs from timeseries data is the differential Hebbian law, which modifies causal connections by correlating time derivatives of FCM node outputs. The differential Hebbian law contrasts with Hebbian outputcorrelation learning laws of adaptive neural networks. FCM nodes represent variable phenomena or fuzzy sets. An FCM node nonlinearly transforms weighted summed inputs into numerical output, again in analogy to a model neuron. Unlike expert systems, which are feedforward search trees, FCMs are nonlinear dynamical systems. FCM resonant states are limit cycles, or timevarying patterns. An FCM limit cycle or hidden pattern is an FCM inference. Experts construct FCMs by drawing causal pictures or digraphs. The corresponding connection matrices are used for inferencing. By additively combining augmented connection matrices, any number of FCMs can be naturally combined into a single knowledge network. The credibility wi in [0, 1] of the ith expert is included in this learning process by multiplying the ith expert's augmented FCM connection matrix by w i. Combining connection matrices is a simple type of adaptive inference. In general, connection matrices are modified by an unsupervised learning law, such as the
Creating Metabolic Network Models using Text Mining and Expert Knowledge
 Atlantic Symposium on Computational Biology and Genome Information Systems & Technology (CBGIST
, 2000
"... RNA profiling analysis and new techniques such as proteomics are yielding vast amounts of data on gene expression and protein levels. This points to the need to develop new methodologies to identify and analyze complex biological networks. This chapter describes the development of a Javabased tool ..."
Abstract

Cited by 6 (3 self)
 Add to MetaCart
RNA profiling analysis and new techniques such as proteomics are yielding vast amounts of data on gene expression and protein levels. This points to the need to develop new methodologies to identify and analyze complex biological networks. This chapter describes the development of a Javabased tool that helps dynamically find and visualize metabolic networks. The tool consists of three parts. The first part is a textmining tool that pulls out potential metabolic relationships from the PubMed database. These relationships are then reviewed by a domain expert and added to an existing network model. The result is visualized using an interactive graph display module. The basic metabolic or regulatory flow in the network is modeled using fuzzy cognitive maps. Causal connections are pulled out from sequence data using a genetic algorithmbased logical proposition generator that searches for temporal patterns in microarray data. Examples from the regulatory and...
Adaptive joint fuzzy sets for function approximation
 Proc. Int. Conf. on Neural Networks “ICNN97
, 1997
"... ..."
Constructing Probability Boxes and . . .
, 2003
"... This report summarizes a variety of the most useful and commonly applied methods for obtaining DempsterShafer structures, and their mathematical kin probability boxes, from empirical information or theoretical knowledge. The report includes a review of the aggregation methods for handling agreement ..."
Abstract
 Add to MetaCart
This report summarizes a variety of the most useful and commonly applied methods for obtaining DempsterShafer structures, and their mathematical kin probability boxes, from empirical information or theoretical knowledge. The report includes a review of the aggregation methods for handling agreement and conflict when multiple such objects are obtained from different sources.
Chapter 9 Creating Metabolic Network Models using Text Mining and Expert Knowledge
"... RNA profiling analysis and new techniques such as proteomics are yielding vast amounts of data on gene expression and protein levels. This points to the need to develop new methodologies to identify and analyze complex biological networks. This chapter describes the development of a ..."
Abstract
 Add to MetaCart
(Show Context)
RNA profiling analysis and new techniques such as proteomics are yielding vast amounts of data on gene expression and protein levels. This points to the need to develop new methodologies to identify and analyze complex biological networks. This chapter describes the development of a