期刊
NEURAL NETWORKS
卷 144, 期 -, 页码 573-590出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.neunet.2021.09.011
关键词
Generative model; Probabilistic inference; Predictive coding; Bayesian inference; Free energy principle; Cognitive development
资金
- Japan Society for the Promotion of Science [16H06569, 16H06566]
- JST CREST [JPMJCR16E2]
- Grants-in-Aid for Scientific Research [16H06566] Funding Source: KAKEN
This article discusses the long-standing aspirations of understanding information processing in the brain and creating general-purpose artificial intelligence, introducing the free energy principle as a useful framework for considering neuronal computation and probabilistic world models. Examples of human behavior and cognition explained under this principle are showcased, demonstrating that probabilistic descriptions of learning and inference are effective ways to create human-like artificial intelligent machines and understand human interactions with the world.
Understanding information processing in the brain-and creating general-purpose artificial intelligence-are long-standing aspirations of scientists and engineers worldwide. The distinctive features of human intelligence are high-level cognition and control in various interactions with the world including the self, which are not defined in advance and are vary over time. The challenge of building human-like intelligent machines, as well as progress in brain science and behavioural analyses, robotics, and their associated theoretical formalisations, speaks to the importance of the world-model learning and inference. In this article, after briefly surveying the history and challenges of internal model learning and probabilistic learning, we introduce the free energy principle, which provides a useful framework within which to consider neuronal computation and probabilistic world models. Next, we showcase examples of human behaviour and cognition explained under that principle. We then describe symbol emergence in the context of probabilistic modelling, as a topic at the frontiers of cognitive robotics. Lastly, we review recent progress in creating human-like intelligence by using novel probabilistic programming languages. The striking consensus that emerges from these studies is that probabilistic descriptions of learning and inference are powerful and effective ways to create human-like artificial intelligent machines and to understand intelligence in the context of how humans interact with their world. (C) 2021 The Author(s). Published by Elsevier Ltd.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据