Complex learning in connectionist networks

摘要

The appropriate choice of a learning algorithm is a central issue in neural network (connectionist network) design. In the literature, a number of such learning methods are available and are broadly classified as supervised, unsupervised and reinforcement learning. This special issue introduces novel complex learning procedures for handling different types of data in several application domains. The six papers in this special issue represent a selection of extended contributions from the World Congress in Nature and Bio-Inspired Computing (NaBIC). Articles were selected on the basis of fundamental ideas and concepts rather than the direct usage of well-established techniques. The special issue is aimed at practitioners and researchers from the academia and industry who are engaged in the development of advanced learning methods from a theoretical perspective and also for data analysis and solving real-world problems. The papers are organized as follows.