Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Dual-Laws Model for a theory of artificial consciousness

Yoshiyuki Ohmura, Yasuo Kuniyoshi

Abstract

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.

Dual-Laws Model for a theory of artificial consciousness

Abstract

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.
Paper Structure (29 sections, 1 figure)

This paper contains 29 sections, 1 figure.

Table of Contents

  1. Introduction
  2. Seven questions
  3. Phenomena
  4. Self
  5. Causation
  6. State
  7. Function
  8. Contents
  9. Universality
  10. Summary
  11. Dual-Laws Model (DLM)
  12. Introduction to DLM
  13. Formalization
  14. Unification with Dual Process Theories
  15. Non-brain centric theory
  16. ...and 14 more sections

Figures (1)

  • Figure 1: Dual-Laws Model (DLM): The supervenience level is composed of multple supervenient functions. The feedback error is the error involved in satisfying the equation defined by combining these supervenient functions. These equations vary according to the index sequences. The dynamical laws at the supervenience level modify and select these discrete index sequences, and these dynamical laws play the role of the "I." At the same time, the feedback error can be adjusted by base level states (e.g., neurons, synapses, and other components) that constitute the supervenient functions. In this way, the feedback error is independently influenced by the index sequences at the supervenience level and by the base level states, making the dual-laws model possible. The base level states are open to environmental and bodily input. This model features two types of feedback control. Type 1 reduces feedback error by adjusting base level states. Type 2 reduces feedback error by modifying index sequences at the supervenience level. Conscious representations are formed by Type 1 feedback control, and they affect the dynamical laws of the supervenience level.