Paper List

期刊: ArXiv Preprint
发布日期: 2026-03-13
Artificial IntelligenceCognitive Science

Dual-Laws Model for a theory of artificial consciousness

Department of mechano-informatics, The University of Tokyo, Japan

Yoshiyuki Ohmura, Yasuo Kuniyoshi
Figure

30秒速读

IN SHORT: This paper addresses the core challenge of developing a comprehensive, testable theory of consciousness that bridges biological and artificial systems, moving beyond narrow generative mechanisms to encompass functional aspects and causal efficacy.

核心创新

  • Methodology Proposes seven fundamental questions (phenomena, self, causation, state, function, contents, universality) as a minimum necessary framework for evaluating consciousness theories, shifting focus from purely generative mechanisms to functional aspects.
  • Theory Introduces the Dual-Laws Model (DLM) that formalizes consciousness through supervenience relationships with independent dynamics at two levels, enabling inter-level causation without relying on neural-specific implementations.
  • Methodology Unifies the DLM with dual-process theories by mapping Type 1 processes to continuous feedback control at the base level and Type 2 processes to discrete algorithmic control at the supervenience level.

主要结论

  • The DLM provides a formal framework where supervenient functions (X_i = b_i(x_i)) enable independent dynamics at two levels, allowing inter-level causation through negative feedback control mechanisms.
  • Conscious systems require two unique capabilities: autonomy in goal construction and cognitive decoupling from external stimuli, distinguishing them from instruction-following machines.
  • The theory rejects panpsychism and single-layer dynamical systems, proposing that consciousness emerges from dual-level feedback control where the supervenience level (corresponding to 'I') modifies index sequences that determine error functions.
研究空白: Current consciousness theories (e.g., Integrated Information Theory, Global Workspace Theory) address only specific aspects, lack universality for artificial systems, and fail to provide comprehensive frameworks that explain both generative mechanisms and functional causality while enabling system design.

摘要: Objectively verifying the generative mechanism of consciousness is extremely difficult because of its subjective nature. As long as theories of consciousness focus solely on its generative mechanism, developing a theory remains challenging. We believe that broadening the theoretical scope and enhancing theoretical unification are necessary to establish a theory of consciousness. This study proposes seven questions that theories of consciousness should address: phenomena, self, causation, state, function, contents, and universality. The questions were designed to examine the functional aspects of consciousness and its applicability to system design. Next, we will examine how our proposed Dual-Laws Model (DLM) can address these questions. Based on our theory, we anticipate two unique features of a conscious system: autonomy in constructing its own goals and cognitive decoupling from external stimuli. We contend that systems with these capabilities differ fundamentally from machines that merely follow human instructions. This makes a design theory that enables high moral behavior indispensable.