Taxonomy of neural transfer functions

Artificial Intelligence and Soft Computing

2012

Abstract. Support Vector Machines (SVM's) with various kernels have become very successful in pattern classification and regression. However, single kernels do not lead to optimal data models. Replacing the input space by a kernel-based feature space in which the linear discrimination problem with margin maximization is solved is a general method that allows for mixing various kernels and adding new types of features. We show here how to generate locally optimized kernels that facilitate multi-resolution and can handle complex data distributions using simpler models than the standard data formulation may provide.

Section: Algorithm 1 Locally Optimized Kernelsmentioning

confidence: 99%

Locally Optimized Kernels

Maszczyk

Artificial Intelligence and Soft Computing

2012

“…Classification probabilities may in such cases be based on a direct calculation of optimal soft-trapezoidal membership functions [6]. Linguistic units of neural networks with LR architecture provide such window-type membership functions, − b)).…”

Section: Application and Optimization Of Rule-based Classifiersmentioning

confidence: 99%

Optimization and Interpretation of Rule-Based Classifiers

Intelligent Information Systems

Jankowski

Grąbczewski

et al. 2000

Abstract. Machine learning methods are frequently used to create rule-based classifiers. For continuous features linguistic variables used in conditions of the rules are defined by membership functions. These linguistic variables should be optimized at the level of single rules or sets of rules. Assuming the Gaussian uncertainty of input values allows to increase the accuracy of predictions and to estimate probabilities of different classes. Detailed interpretation of relevant rules is possible using (probabilistic) confidence intervals. A real life example of such interpretation is given for personality disorders. The approach to optimization and interpretation described here is applicable to any rule-based system.

“…Oblique distribution of data may require linear combination, or non-linear transformation, of input features [9]. The meaning of rules build with such features may be difficult to comprehend.…”

Section: Types Of Rulesmentioning

confidence: 99%

Prototype based rules-a new way to understand the data

IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222)

Grudziński²

Self Cite

Abstract.Logical rules are not the only way to understand the structure of data. Prototype-based rules evaluate similarity to a small set of prototypes using optimized similarity measures. Such rules include crisp and fuzzy logic rules as special cases and are natural way of categorization from psychological point of view. An elimination procedure selecting good prototypes from a training set has been described. Illustrative applications on several datasets show that a few prototypes may indeed explain the data structure.