Robust Intelligent Systems

Robustness is an intriguing phenomenon in many complex intelligent systems, natural and artificial alike. This book investigates the relevance of robustness in a modern intelligent computing context, where many systems take inspiration from fundamental problem-solving strategies found in nature such as redundancy, granularity, adaptation, repair, and self-healing for creating robust systems. The book explores the value these strategies may have as general design principles in a diverse range of areas including the computer technology underlying many intelligent systems, and also systems and applications inspired by biology, artificial intelligence, and intelligent space exploration. The topics covered include computer hardware and software, networks and protocols, brain-computer interfaces, biological networks and immune systems, humanoid robotics, image processing, artificial neural networks, genetic algorithms, chaos theory, and other soft computing techniques, as well as space system design and bio-regenerative life support systems.

"Using artificial intelligence and robustness as a unifying theme, this book comments on the fundamental strategies found in nature (such as redundancy, granularity, adaptation, repair, self-healing, etc.), and how an understanding of these can be used to further research into general design principles for artificial intelligence in the context of a diverse range of modern research areas and systems (including pervasive computing, autonomic computing, ambient intelligence, bioinformatics and others).

Robustness in Computer Hardware, Software, Networks, and Protocols.- Robustness in Digital Hardware.- Multiagent-Based Fault Tolerance Management for Robustness.- A Two-Level Robustness Model for Self-Managing Software Systems.- Robustness in Network Protocols and Distributed Applications of the Internet.- Robustness in Biology Inspired Systems.- Detecting Danger: The Dendritic Cell Algorithm.- Non-invasive Brain-Computer Interfaces for Semi-autonomous Assistive Devices.- Robust Learning of High-dimensional Biological Networks with Bayesian Networks.- Robustness in Artificial Intelligence Systems.- Robustness in Nature as a Design Principle for Artificial Intelligence.- Feedback Structures as a Key Requirement for Robustness: Case Studies in Image Processing.- Exploiting Motor Modules in Modular Contexts in Humanoid Robotics.- Robustness in Space Applications.- Robustness as Key to Success for Space Missions.- Robust and Automated Space System Design.- Robust Bio-regenerative Life Support Systems Control.