Output details
13 - Electrical and Electronic Engineering, Metallurgy and Materials
University of Southampton
A forward-constrained regression algorithm for sparse kernel density estimation
Significance of output:
The estimation of the probability density function (pdf) from observed data samples is a fundamental problem in many machine learning and pattern recognition applications. Our novel approach achieves efficient and accurate pdf estimates utilising the minimum number. of parameters and the minimum number of iterations and as such is the most effective approach available. It can be used in regression, classification and data fusion problems, such as metal fatigue and cancer diagnostics, both of which are topical and carry significant societal importance. The proposed approach is simple to implement and the associated computational cost is very low.
