arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.04589cs.AI
收藏

基于先验引导随机搜索算法的综合信息优化

Optimizing Integrated Information with a Prior Guided Random Search Algorithm

Universidad Pontificia Comillas(卡米亚斯大主教大学);Universidad de Navarra(纳瓦拉大学)

Eduardo C. Garrido-Merchán, Javier Sánchez-Cañizares

摘要:

整合信息论(Integrated Information Theory,IIT)是一个理论框架,它提供了一个定量的度量来估计一个物理系统何时是有意识的,它的意识程度,以及系统正在经历的感受质空间的复杂性。形式上,IIT基于这样的假设:如果一个替代的物理系统可以完全嵌入意识的现象学属性,那么系统属性必须受到所体验的感受质属性的约束。根据这个假设,IIT将物理系统表示为互连元素的网络,可以将其视为概率因果图$\mathcal{G}$,其中每个节点具有输入输出函数,并且所有图都编码在转移概率矩阵中。因此,IIT的意识,$Φ$的定量测量,计算相对于转移概率矩阵和当前状态的图形。在本文中,我们提供了一个随机搜索算法,能够优化$Φ$,以调查,随着节点数量的增加,具有较高的$Φ$的图形的结构。我们还提供了参数,显示了应用更复杂的黑盒搜索算法,如贝叶斯优化或元分析,在这个特定的问题的困难。此外,我们建议这些技术的具体研究线,以提高搜索算法,保证最大的$Φ$。

英文摘要:

Integrated information theory (IIT) is a theoretical framework that provides a quantitative measure to estimate when a physical system is conscious, its degree of consciousness, and the complexity of the qualia space that the system is experiencing. Formally, IIT rests on the assumption that if a surrogate physical system can fully embed the phenomenological properties of consciousness, then the system properties must be constrained by the properties of the qualia being experienced. Following this assumption, IIT represents the physical system as a network of interconnected elements that can be thought of as a probabilistic causal graph, $\mathcal{G}$, where each node has an input-output function and all the graph is encoded in a transition probability matrix. Consequently, IIT's quantitative measure of consciousness, $Φ$, is computed with respect to the transition probability matrix and the present state of the graph. In this paper, we provide a random search algorithm that is able to optimize $Φ$ in order to investigate, as the number of nodes increases, the structure of the graphs that have higher $Φ$. We also provide arguments that show the difficulties of applying more complex black-box search algorithms, such as Bayesian optimization or metaheuristics, in this particular problem. Additionally, we suggest specific research lines for these techniques to enhance the search algorithm that guarantees maximal $Φ$.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑