A whole brain probabilistic generative model: Toward realizing cognitive architectures for developmental robots
A whole brain probabilistic generative model: Toward realizing cognitive architectures for developmental robots
复制标题
DOI：
10.1016/j.neunet.2022.02.026
复制
发表时间：
2021-03
期刊：
影响因子：
--
通讯作者：
T. Taniguchi;H. Yamakawa;T. Nagai;K. Doya;M. Sakagami;Masahiro Suzuki;Tomoaki Nakamura;Akira Taniguchi
中科院分区：
文献类型：
--
作者：
T. Taniguchi;H. Yamakawa;T. Nagai;K. Doya;M. Sakagami;Masahiro Suzuki;Tomoaki Nakamura;Akira Taniguchi
构建一个类似人类的综合性人工认知系统，即人工通用智能(AGI)，是人工智能(AI)领域的圣杯。此外，能够使人工系统实现认知发展的计算模型将是大脑和认知科学的极好参考。本文描述了一种通过集成基本认知模块来开发认知体系结构的方法，以使这些模块能够作为一个整体进行训练。该方法基于两个思想：(1)脑启发人工智能，学习人脑结构来构建人类级别的智能；(2)基于概率生成模型(PGM)的认知结构，通过集成概率生成模型来开发开发机器人的认知系统。提出的开发框架被称为全脑PGM(WB-PGM)，它与现有的认知结构有根本的不同，它可以通过一个基于感觉-运动信息的系统来持续学习。本文描述了WB-PGM的基本原理，基于全脑PGM的基本认知模块的现状，它们与人脑的关系，认知模块的整合方法，以及未来的挑战。我们的发现可以作为脑研究的参考。由于PGMS描述了变量之间的明确信息关系，WB-PGM提供了从计算科学到脑科学的可解释的指导。通过提供这样的信息，神经科学的研究人员可以向人工智能和机器人领域的研究人员提供反馈，说明目前的模型在参考大脑方面所缺乏的东西。此外，它还可以促进神经认知科学以及人工智能和机器人领域的研究人员之间的合作。
Building a human-like integrative artificial cognitive system, that is, an artificial general intelligence (AGI), is the holy grail of the artificial intelligence (AI) field. Furthermore, a computational model that enables an artificial system to achieve cognitive development will be an excellent reference for brain and cognitive science. This paper describes an approach to develop a cognitive architecture by integrating elemental cognitive modules to enable the training of the modules as a whole. This approach is based on two ideas: (1) brain-inspired AI, learning human brain architecture to build human-level intelligence, and (2) a probabilistic generative model (PGM)-based cognitive architecture to develop a cognitive system for developmental robots by integrating PGMs. The proposed development framework is called a whole brain PGM (WB-PGM), which differs fundamentally from existing cognitive architectures in that it can learn continuously through a system based on sensory-motor information.In this paper, we describe the rationale for WB-PGM, the current status of PGM-based elemental cognitive modules, their relationship with the human brain, the approach to the integration of the cognitive modules, and future challenges. Our findings can serve as a reference for brain studies. As PGMs describe explicit informational relationships between variables, WB-PGM provides interpretable guidance from computational sciences to brain science. By providing such information, researchers in neuroscience can provide feedback to researchers in AI and robotics on what the current models lack with reference to the brain. Further, it can facilitate collaboration among researchers in neuro-cognitive sciences as well as AI and robotics.