A New Definition of Sensitivity for RBFNN and Its Applications to Feature Reduction
نویسندگان
چکیده
Due to the existence of redundant features, the Radial-Basis Function Neural Network (RBFNN) which is trained from a dataset is likely to be huge. Sensitivity analysis technique usually could help to reduce the features by deleting insensitive features. Considering the perturbation of network output as a random variable, this paper defines a new sensitivity formula which is the limit of variance of output perturbation with respect to the input perturbation going to zero. To simplify the sensitivity expression and computation, we prove that the exchange between limit and variance is valid. A formula for computing the new sensitivity of individual features is derived. Numerical simulations show that the new sensitivity definition can be used to remove irrelevant features effectively.
منابع مشابه
Feature Selection in Structural Health Monitoring Big Data Using a Meta-Heuristic Optimization Algorithm
This paper focuses on the processing of structural health monitoring (SHM) big data. Extracted features of a structure are reduced using an optimization algorithm to find a minimal subset of salient features by removing noisy, irrelevant and redundant data. The PSO-Harmony algorithm is introduced for feature selection to enhance the capability of the proposed method for processing the measure...
متن کاملApplying Genetic Algorithm to EEG Signals for Feature Reduction in Mental Task Classification
Brain-Computer interface systems are a new mode of communication which provides a new path between brain and its surrounding by processing EEG signals measured in different mental states. Therefore, choosing suitable features is demanded for a good BCI communication. In this regard, one of the points to be considered is feature vector dimensionality. We present a method of feature reduction us...
متن کاملSupervised Feature Extraction of Face Images for Improvement of Recognition Accuracy
Dimensionality reduction methods transform or select a low dimensional feature space to efficiently represent the original high dimensional feature space of data. Feature reduction techniques are an important step in many pattern recognition problems in different fields especially in analyzing of high dimensional data. Hyperspectral images are acquired by remote sensors and human face images ar...
متن کاملSensitivity based Generalization Error for Supervised Learning Problem with Applications in Model Selection and Feature Selection
Generalization error model provides a theoretical support for a classifier's performance in terms of prediction accuracy. However, existing models give very loose error bounds. This explains why classification systems generally rely on experimental validation for their claims on prediction accuracy. In this talk we will revisit this problem and explore the idea of developing a new generalizatio...
متن کاملکاهش ابعاد دادههای ابرطیفی به منظور افزایش جداییپذیری کلاسها و حفظ ساختار داده
Hyperspectral imaging with gathering hundreds spectral bands from the surface of the Earth allows us to separate materials with similar spectrum. Hyperspectral images can be used in many applications such as land chemical and physical parameter estimation, classification, target detection, unmixing, and so on. Among these applications, classification is especially interested. A hyperspectral im...
متن کامل