Vendor-supplied metadata.

Includes bibliographical references and index.

Bio-inspired techniques are based on principles, or models, of biological systems. In general, natural systems present remarkable capabilities of resilience and adaptability. In this book, we explore how bio-inspired methods can solve different problems linked to computer networks.

Machine generated contents note: ch. 1 Evolution and Evolutionary Algorithms -- 1.1. Brief introduction to evolution -- 1.2. Mechanisms of evolution -- 1.2.1. DNA code -- 1.2.2. Mutation -- 1.2.3. Sexual reproduction and recombination -- 1.2.4. Natural selection -- 1.2.5. Genetic drift -- 1.3. Artificial evolution -- 1.3.1. The basic process -- 1.3.2. Limitations -- 1.4. Applications on networks -- 1.4.1.Network positioning -- 1.4.2. Routing -- 1.4.3. Other works -- 1.5. Further reading -- 1.6. Bibliography -- ch. 2 Chemical Computing -- 2.1. Artificial chemistry -- 2.2. Applications on networks -- 2.2.1. Data dissemination -- 2.2.2. Routing -- 2.3. Further reading -- 2.4. Bibliography -- ch. 3 Nervous System -- 3.1. Nervous system hierarchy -- 3.1.1. Central nervous system -- 3.1.2. Peripheral nervous system -- 3.2. The neuron -- 3.3. The neocortex -- 3.4. Speed and capacity -- 3.5. Artificial neural networks -- 3.5.1. The perceptron -- 3.5.2. Interconnecting perceptrons -- 3.5.3. Learning process.

Note continued: 3.5.4. The backpropagation algorithm -- 3.6. Applications on networks -- 3.6.1. ANN in intrusion detection systems -- 3.6.2. Fault detection -- 3.6.3. Routing -- 3.7. Further reading -- 3.8. Bibliography -- ch. 4 Swarm Intelligence (SI) -- 4.1. Ant colony optimization -- 4.2. Applications on networks -- 4.2.1. Ants colony on routing -- 4.2.2. Ants colony on intrusion detection -- 4.3. Particle swarm optimization -- 4.4. Applications on networks -- 4.4.1. Particle swarm on node positioning -- 4.4.2. Particle swarm on intrusion detection -- 4.5. Further reading -- 4.6. Bibliography.