Editorial

The research into neural information processing aims to develop computational tools for understanding how the human brain works as well as how to apply this knowledge to build artificial intelligence systems. It is a multidisciplinary research area, attracting researchers from both biological learning systems and artificial learning systems. Nowadays, the focus in that area covers a wide spectrum in relation with machine learning, artificial intelligence, cognitive science, as well as computational neuroscience. This would lead to creation ofmore powerful brain-inspired machine learning models based on better understanding of human brains. On the other hand, phenomena and principles found from nature offer a valuable insight and perspective of how effective learning can be conducted in both biological and artificial systems. Many intelligent methods based on natural principles have been developed to facilitate new models of learning across different domains. Nature inspired learning is now an active research field, where a variety of theories and approaches originating from the natural world, particularly from biological and physical systems, are being exploited to address complex learning tasks that are hard to handle with conventional learning techniques. The special issue aims to explore the relationship between Nature-Inspired Learning and Neural Information Processing and to find new ways to bridge these two exciting research areas for building hybrid systemswith stronger learning capability. The 14 high quality papers in this issue are selected froma total of 87 submissions, some ofwhichwere extended versions of papers in the 2014 10th International Conference on Natural Computation (ICNC 2014) and the 2014 11th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD 2014), after three rounds of review. In the following we provide a brief introduction to each accepted paper.