更改

[[文件:截屏2024-12-14 21.49.16.png|替代=|无框|500x500像素]]

[[文件:截屏2024-12-14 21.49.16.png|替代=|无框|500x500像素]]

=测量层间连通性的联合效应=

=有效信息量化联合效应与独立效应=

综合信息理论（IIT）已被用于评估系统中联合效应与独立效应所包含的总信息<ref>Giulio Tononi.  Consciousness as integrated information:  a provisional manifesto. The Biological Bulletin, 215(3): 216–242, 2008.</ref>。它是因果分析的有用工具，分析网络因果结构中整合的信息量<ref>William Marshall, Hyunju Kim, Sara I Walker, Giulio Tononi, and Larissa Albantakis. How causal analysis can reveal autonomy  in  models  of  biological  systems. Philosophical  Transactions  of  the  Royal  Society  A:  Mathematical, Physical and Engineering Sciences, 375(2109):20160358, 2017.</ref><ref name=":4">Larissa Albantakis, William Marshall, Erik Hoel, and Giulio Tononi.  What caused what?  a quantitative account of actual causation using dynamical causal networks. Entropy, , 21(5):459, 2019.</ref>。以前，综合信息被衡量为给定分区的EI损失<ref>David Balduzzi and Giulio Tononi.  Integrated information in discrete dynamical systems: motivation and theoretical framework. PLoS Comput Biol, 4(6):e1000091, 2008.</ref>，使EI成为综合信息的上限。然而，目前还没有一种公认的通用综合信息衡量标准<ref>Masafumi Oizumi, Larissa Albantakis, and Giulio Tononi. From the phenomenology to the mechanisms of consciousness: integrated information theory 3.0. PLoS Comput Biol, 10(5):e1003588, 2014.</ref>。相反，在不同的系统中提出了各种集成信息的措施<ref>Max Tegmark. Improved measures of integrated information. PLoS computational biology, 12(11):e1005123, 2016.</ref><ref>Pedro AM Mediano, Anil K Seth, and Adam B Barrett.  Measuring integrated information: Comparison of candidate measures in theory and simulation. Entropy, 21(1):17, 2019.</ref>。传统上，前馈网络中的集成信息量为零，因为没有可重入连接，因为它基于在系统的所有可能子集中找到最小信息分区。然而，即使在前馈网络中，一层的节点仍然可能对另一层产生不可约的联合效应，因此我们引入了一种度量，即前馈集成信息，应用于DNN。       

综合信息理论（IIT）已被用于评估系统中联合效应与独立效应所包含的总信息<ref>Giulio Tononi.  Consciousness as integrated information:  a provisional manifesto. The Biological Bulletin, 215(3): 216–242, 2008.</ref>。它是因果分析的有用工具，分析网络因果结构中整合的信息量<ref>William Marshall, Hyunju Kim, Sara I Walker, Giulio Tononi, and Larissa Albantakis. How causal analysis can reveal autonomy  in  models  of  biological  systems. Philosophical  Transactions  of  the  Royal  Society  A:  Mathematical, Physical and Engineering Sciences, 375(2109):20160358, 2017.</ref><ref name=":4">Larissa Albantakis, William Marshall, Erik Hoel, and Giulio Tononi.  What caused what?  a quantitative account of actual causation using dynamical causal networks. Entropy, , 21(5):459, 2019.</ref>。以前，综合信息被衡量为给定分区的EI损失<ref>David Balduzzi and Giulio Tononi.  Integrated information in discrete dynamical systems: motivation and theoretical framework. PLoS Comput Biol, 4(6):e1000091, 2008.</ref>，使EI成为综合信息的上限。然而，目前还没有一种公认的通用综合信息衡量标准<ref>Masafumi Oizumi, Larissa Albantakis, and Giulio Tononi. From the phenomenology to the mechanisms of consciousness: integrated information theory 3.0. PLoS Comput Biol, 10(5):e1003588, 2014.</ref>。相反，在不同的系统中提出了各种集成信息的措施<ref>Max Tegmark. Improved measures of integrated information. PLoS computational biology, 12(11):e1005123, 2016.</ref><ref>Pedro AM Mediano, Anil K Seth, and Adam B Barrett.  Measuring integrated information: Comparison of candidate measures in theory and simulation. Entropy, 21(1):17, 2019.</ref>。传统上，前馈网络中的集成信息量为零，因为没有可重入连接，因为它基于在系统的所有可能子集中找到最小信息分区。然而，即使在前馈网络中，一层的节点仍然可能对另一层产生不可约的联合效应，因此我们引入了一种度量，即前馈集成信息，应用于DNN。