Rapid developments in computing-related technologies have enabled the collection of large amounts of data at unprecedented rates from diverse systems, both natural and engineered. The availability of such data has motivated the development of intelligent systems to gain new insights into how these systems work, leading thereby to superior decision making. In this paper we present recent advances in using hybrid soft computing techniques to achieve two of the core functionalities needed to build such intelligent systems, namely: feature selection and classifier design. We posit that these two functionalities are coupled and must be solved simultaneously. We give an overview of soft computing techniques, of classification and classifier design, of the concept of feature extraction and feature selection, of hybrid soft computing techniques, and we present approaches for simultaneous feature selection and classifier design using hybrid soft computing techniques. The paper concludes with insights and directions for future work.