Brain-inspired and Self-based Artificial Intelligence

2024-02-29

arXiv.org

AI Summary

Current AI systems lack self-awareness and subjective experience, hindering the realization of genuine artificial general intelligence (AGI). Method: This paper proposes a brain-inspired AGI paradigm centered on the “self,” formalized as a five-layer self-organizing framework encompassing perceptual learning, bodily self, agentic self, social self, and conceptual self. It introduces, for the first time, a hierarchical self-theory integrating cognitive neuroscience modeling, embodied perception–action loops, multi-scale self-organized learning, social interaction reasoning, and conceptual abstraction. Contribution/Results: The framework overcomes fundamental limitations of existing AI in self-reference, subjective understanding, and socio-cognitive coordination. By positioning the self as an endogenous driver of consciousness emergence and cognitive evolution, it provides a theoretically grounded and architecturally feasible pathway toward AGI endowed with subjective awareness, autonomous adaptation, and socially situated intelligence.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent/AI Theories and Architectures
• Philosophy and Ethics of AI: Artificial General Intelligence

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

The question"Can machines think?"and the Turing Test to assess whether machines could achieve human-level intelligence is one of the roots of AI. With the philosophical argument"I think, therefore I am", this paper challenge the idea of a"thinking machine"supported by current AIs since there is no sense of self in them. Current artificial intelligence is only seemingly intelligent information processing and does not truly understand or be subjectively aware of oneself and perceive the world with the self as human intelligence does. In this paper, we introduce a Brain-inspired and Self-based Artificial Intelligence (BriSe AI) paradigm. This BriSe AI paradigm is dedicated to coordinating various cognitive functions and learning strategies in a self-organized manner to build human-level AI models and robotic applications. Specifically, BriSe AI emphasizes the crucial role of the Self in shaping the future AI, rooted with a practical hierarchical Self framework, including Perception and Learning, Bodily Self, Autonomous Self, Social Self, and Conceptual Self. The hierarchical framework of the Self highlights self-based environment perception, self-bodily modeling, autonomous interaction with the environment, social interaction and collaboration with others, and even more abstract understanding of the Self. Furthermore, the positive mutual promotion and support among multiple levels of Self, as well as between Self and learning, enhance the BriSe AI's conscious understanding of information and flexible adaptation to complex environments, serving as a driving force propelling BriSe AI towards real Artificial General Intelligence.

Problem

• Assessing if machines achieve human-level intelligence without self-awareness
• Developing self-based AI for human-like perception and understanding
• Creating hierarchical Self framework to advance Artificial General Intelligence

Innovation

• Brain-inspired self-based AI paradigm
• Hierarchical Self framework integration
• Self-organized cognitive functions coordination