- ホーム
- > 洋書
- > 英文書
- > Computer / General
Full Description
Complex cognitive systems, such as social networks, robotic swarms, or biological networks, are composed of individual entities (the agents) whose actions typically arise from some sophisticated form of "social" interaction with other agents. For example, consider the way humans form their individual opinions about a certain phenomenon. The opinions take shape via repeated interactions with other individuals (also called neighbors), whether through physical contact or virtually.
A diffusion mechanism emerges through which opinions, information, or even fake news propagate across the network. Distributed social learning strategies arise also over man-engineered systems. Consider a robotic swarm deployed over a hazardous area, where some robots operating under disadvantageous conditions (e.g., with limited visibility or partial information) would only be able to perform their actions (such as saving a life during a rescue operation) by leveraging significant cooperation from other robots that may have better access to critical information.
Nature itself provides many other excellent examples of cooperative learning through the sophisticated dynamics over biological networks. We will generally refer to these types of systems as multi-agent networks.
Contents
1. Introduction
2. Bayesian Learning
3. From Single-Agent to Social Learning
4. Network Models
5. Social Learning with Geometric Averaging
6. Error Probability Performance
7. Social Learning with Arithmetic Averaging
8. Adaptive Social Learning
9. Learning Accuracy under ASL
10. Adaptation under ASL
11. Partial Information Sharing
12. Social Machine Learning
Extensions, Conclusions, Appendices
