Squiggly Lines and Random Dots—You Can Fit Anything with a Nonlinear Model

摘要: This chapter describes the advances made in methodological aspects of modelling skin permeability by considering artificial intelligence, fuzzy logic and advanced Machine Learning methods how they have been applied to absorption. It reviews often-stunted contribution field these advantages such produced recent years. In addition, also considers problems with methods, particularly lack use due need for specific computational expertise that is not normally associated development quantitative structure–permeability models, discusses widespread can be tackled. as this models often fall into “black box” category do therefore present a readily usable algorithm, an explicit output used discern mechanistic process are discussed. These include feature selection which shown non-independence interrelationship key descriptors on each other algorithm discrete expressions may limited value.