Evolving Connectionist Systems for Adaptive Learning and Knowledge Discovery: A Review of Principles and Applications: From Neuro-fuzzy-, to Spiking-, Neurogenetic- and Quantum Inspired

This chapter follows the development of a class of neural networks called evolving connectionist systems (ECOS). ECOS combine the adaptive/evolving learning ability of neural networks and the approximate reasoning and linguistically meaningful explanation features of symbolic representation, such as fuzzy rules. This review paper includes principles and applications of hybrid expert systems, evolving neuro-fuzzy systems, evolving spiking neural networks, neurogenetic systems, and quantum inspired systems, all discussed from the point of few of their adaptability and model interpretability. The chapter covers both methods and their numerous applications for data modelling, predictive systems, data mining, pattern recognition, across application areas of engineering, medicine and health, neuroinformatics, bioinformatics, adaptive robotics, etc.