So near and yet so far: New insight into properties of some well-known classifier paradigms

Fisch, Dominik; Kühbeck, Bernhard; Sick, Bernhard; Ovaska, S.J.

doi:10.1016/j.ins.2010.05.030

Cited by 25 publications

(14 citation statements)

References 69 publications

(69 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Advanced training techniques for generative RBF classifiers that allow for a detection of novel kinds of input patterns are presented in [63] and novelty detection techniques based on such classifiers are introduced in [79]. Finally, [68] compares the properties of various classifiers including RBF from a more theoretical viewpoint.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

On the versatility of radial basis function neural networks: A case study in the field of intrusion detection

Fisch

Hofmann

Sick

2010

Information Sciences

Self Cite

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

“…As a consequence, a minor modification of the learning task (e.g., slightly different data or parameters) may lead to an SVM with almost the same decision boundary, but different support vectors and, thus, different rules. This would be a very bad precondition for understandability [68].…”

Section: Rule Sets Inherent To Bnmentioning

confidence: 99%

On the versatility of radial basis function neural networks: A case study in the field of intrusion detection

Fisch

Hofmann

Sick

2010

Information Sciences

Self Cite

View full text Add to dashboard Cite

“…According to [7], the conjugate prior of a multinomial is a Dirichlet distribution and the conjugate prior of a multivariate normal is a normal-Wishart distribution. The Bayesian knowledge fusion focuses on the 2nd category.…”

Section: Distributed Intrusion Detectionmentioning

confidence: 99%

Knowledge Fusion Technique Using Classifier Ensemble by Different Classification Rules

Nandedkar¹

2015

IJIRCCE

View full text Add to dashboard Cite

Classification rules are extracted from sample data known as knowledge. If we extract these knowledge in a distributed way, it is necessary to combine or fuse these rules. The task of data fusion is to identify the true values of data items among multiple observed values drawn from different sources of varying reliability. In data mining applications knowledge extraction is splitted into subtasks due to memory or run-time limitations. Again, locally extracted knowledge must be consolidated later because communication overhead should be low. Extracting information from multiple data sources, and reconciling the values so the true values can be stored in a central data repository. But it's a problem of vital importance to the database and knowledge management communities.In a conventional approach extracting knowledge is typically done either by combining the classifiers' outputs or by combining the sets of classification rules but in this paper, I introduce a new way of fusing classifiers at the level of parameters of classification rules. Here its focused around the utilization of probabilistic generative classifiers utilizing multinomial circulations and multivariate ordinary dispersions for the consistent ones. We are using these distributions as hyper distributions or second-order distributions. Fusing of these classifiers are can be done by multiplying the hyper-distributions of the parameters.

show abstract

“…However, beyond providing an alternative theoretical way of understanding and measuring information as a representational and cognitive quantity, the notion of representational information and its measurement may be useful in more pragmatic settings. Some potential applications of the present theory include: (1) database analysis, (2) rule mining as in [27], (3) modeling and implementation of conceptual processes in artificial and human cognitive systems (e.g., artificial classifiers as in [10], robot perception as in [12], and AI experts), and 4) information compression.…”

Section: Potential Applicationsmentioning

confidence: 99%

Representational information: a new general notion and measure of information

Vigo

2011

Information Sciences

View full text Add to dashboard Cite

a b s t r a c tIn what follows, we introduce the notion of representational information (information conveyed by sets of dimensionally defined objects about their superset of origin) as well as an original deterministic mathematical framework for its analysis and measurement. The framework, based in part on categorical invariance theory [30], unifies three key constructs of universal science -invariance, complexity, and information. From this unification we define the amount of information that a well-defined set of objects R carries about its finite superset of origin S, as the rate of change in the structural complexity of S (as determined by its degree of categorical invariance), whenever the objects in R are removed from the set S. The measure captures deterministically the significant role that context and category structure play in determining the relative quantity and quality of subjective information conveyed by particular objects in multi-object stimuli.

show abstract

So near and yet so far: New insight into properties of some well-known classifier paradigms

Cited by 25 publications

References 69 publications

On the versatility of radial basis function neural networks: A case study in the field of intrusion detection

On the versatility of radial basis function neural networks: A case study in the field of intrusion detection

Knowledge Fusion Technique Using Classifier Ensemble by Different Classification Rules

Representational information: a new general notion and measure of information

Contact Info

Product

Resources

About