Global Adaptation in Networks of Selfish Components: Emergent Associative Memory at the System Scale
Global Adaptation in Networks of Selfish Components: Emergent Associative Memory at the System Scale
复制标题
自私组件网络的全局适应：系统规模的涌现联想记忆
DOI：
10.1162/artl_a_00029
复制
发表时间：
2011
期刊：
影响因子：
2.6
通讯作者：
C. Buckley
中科院分区：
文献类型：
--
作者：
R. Watson;Rob Mills;C. Buckley
在某些情况下，复杂的自适应系统由许多自利的代理人可以自组织成结构，提高全球适应，效率或功能。然而，这种结果的一般条件知之甚少，并提出了一个基本的开放问题，如生态学，社会学，经济学，生物学和技术基础设施设计等领域。相比之下，人工神经网络形成执行集体计算过程（诸如关联记忆/回忆、分类、泛化和优化）的结构的充分条件是很好理解的。这种在单一药剂或生物体内的全局功能并不完全令人惊讶，因为机制（例如，但是，多智能体系统中的智能体没有明显的理由去遵守这样一个结构化协议，或者在从个人利益出发时产生这样的全局行为。然而，赫布学习实际上是一个非常简单和完全分布的习惯或正反馈原则。在这里，我们表明，当自私的代理人可以修改他们受到其他代理人影响的方式时（例如，当他们可以影响其他代理人，他们互动），那么，在适应这些代理人之间的关系，以最大限度地提高自己的效用，他们将必然改变他们的方式同源赫布学习。具有适应性关系的多智能体系统将表现出与赫布学习下的神经网络相同的系统级行为。例如，在多智能体系统中提高全局效率可以解释为联想记忆的固有能力，通过理想化存储的模式和/或创建新的子模式组合来概括。因此，分布式多智能体系统可以自发地表现出自适应的全局行为，在相同的意义上，并通过相同的机制，与组织学习的联结主义模型中熟悉的组织原则。
In some circumstances complex adaptive systems composed of numerous self-interested agents can self-organize into structures that enhance global adaptation, efficiency, or function. However, the general conditions for such an outcome are poorly understood and present a fundamental open question for domains as varied as ecology, sociology, economics, organismic biology, and technological infrastructure design. In contrast, sufficient conditions for artificial neural networks to form structures that perform collective computational processes such as associative memory/recall, classification, generalization, and optimization are well understood. Such global functions within a single agent or organism are not wholly surprising, since the mechanisms (e.g., Hebbian learning) that create these neural organizations may be selected for this purpose; but agents in a multi-agent system have no obvious reason to adhere to such a structuring protocol or produce such global behaviors when acting from individual self-interest. However, Hebbian learning is actually a very simple and fully distributed habituation or positive feedback principle. Here we show that when self-interested agents can modify how they are affected by other agents (e.g., when they can influence which other agents they interact with), then, in adapting these inter-agent relationships to maximize their own utility, they will necessarily alter them in a manner homologous with Hebbian learning. Multi-agent systems with adaptable relationships will thereby exhibit the same system-level behaviors as neural networks under Hebbian learning. For example, improved global efficiency in multi-agent systems can be explained by the inherent ability of associative memory to generalize by idealizing stored patterns and/or creating new combinations of subpatterns. Thus distributed multi-agent systems can spontaneously exhibit adaptive global behaviors in the same sense, and by the same mechanism, as with the organizational principles familiar in connectionist models of organismic learning.
影响因子：
8.6
作者：
Pacheco, Jorge M.;Traulsen, Arne;Nowak, Martin A.
通讯作者：
Nowak, Martin A.
DOI：
10.1073/pnas.0305059101
发表时间：
2004-07-27
影响因子：
11.1
作者：
Werfel, J;Bar-Yam, Y
通讯作者：
Bar-Yam, Y