Synergistic information supports modality integration and flexible learning in neural networks solving multiple tasks
Synergistic information supports modality integration and flexible learning in neural networks solving multiple tasks
复制标题
协同信息支持解决多个任务的神经网络中的模态集成和灵活学习
DOI：
10.1371/journal.pcbi.1012178
复制
发表时间：
2022
影响因子：
4.3
通讯作者：
P. Mediano
中科院分区：
文献类型：
--
作者：
A. Proca;F. Rosas;A. Luppi;D. Bor;Matthew Crosby;P. Mediano
通过分析大脑如何参与不同的信息处理模式，在理解认知方面取得了惊人的进展。例如，所谓的协同信息（由一组神经元编码的信息，而不是由任何子集编码的信息）在与复杂认知相关的人脑区域中起着关键作用。然而，有两个问题仍然没有答案：（a）认知系统如何以及为什么可以变得高度协同;（B）信息状态如何映射到各种学习模式的人工神经网络上。在这里，我们采用了一个信息分解框架来研究神经网络执行认知任务。我们的研究结果表明，随着网络学习多个不同的任务，协同作用会增加，并且在需要整合多个来源的任务中，性能严重依赖于协同神经元。总的来说，我们的研究结果表明，协同作用是用来联合收割机信息从多种模式，更普遍的灵活和有效的学习。这些研究结果揭示了新的方法来调查如何以及为什么学习系统采用特定的信息处理策略，并支持的原则，即通用学习的能力严重依赖于系统的信息动态。
Striking progress has been made in understanding cognition by analyzing how the brain is engaged in different modes of information processing. For instance, so-called synergistic information (information encoded by a set of neurons but not by any subset) plays a key role in areas of the human brain linked with complex cognition. However, two questions remain unanswered: (a) how and why a cognitive system can become highly synergistic; and (b) how informational states map onto artificial neural networks in various learning modes. Here we employ an information-decomposition framework to investigate neural networks performing cognitive tasks. Our results show that synergy increases as networks learn multiple diverse tasks, and that in tasks requiring integration of multiple sources, performance critically relies on synergistic neurons. Overall, our results suggest that synergy is used to combine information from multiple modalities-and more generally for flexible and efficient learning. These findings reveal new ways of investigating how and why learning systems employ specific information-processing strategies, and support the principle that the capacity for general-purpose learning critically relies on the system's information dynamics.
DOI：
10.48550/arxiv.2203.11815
发表时间：
2022-03
期刊：
ArXiv
影响因子：
--
作者：
Richard D. Lange;D. Rolnick;K. Kording
通讯作者：
Richard D. Lange;D. Rolnick;K. Kording
影响因子：
25
作者：
Yang, Guangyu Robert;Joglekar, Madhura R.;Wang, Xiao-Jing
通讯作者：
Wang, Xiao-Jing
影响因子：
16.6
作者：
Johnston WJ;Fusi S
通讯作者：
Fusi S