The Limits to Machine Consciousness

It is generally accepted that machines can replicate cognitive tasks performed by conscious agents as long as they are not based on the capacity of awareness. We consider several views on the nature of subjective awareness, which is fundamental for self-reflection and review, and present reasons why this property is not computable. We argue that consciousness is more than an epiphenomenon and assuming it to be a separate category is consistent with both quantum mechanics and cognitive science. We speak of two kinds of consciousness, little-C and big-C, and discuss the significance of this classification in analyzing the current academic debates in the field. The interaction between the system and the measuring apparatus of the experimenter is examined both from the perspectives of decoherence and the quantum Zeno effect. These ideas are used as context to address the question of limits to machine consciousness.

The Logic Fundamentals of Machine Consciousness: Theory of Tri-State

For a long time, the system of scientific methodology has been composed of logic, empirical (falsification), qualitative, quantitative and deterministic, and corresponding thinking tools. However, under the background of complexity science, the category of methodology should be changed, that is, on the basis of traditional methodology, non-classical logic, hierarchy, stereotype (topological invariant) and uncertainty should be added. This is also the main idea behind the “Thoery of Tri-state” in the first part of this paper. The core idea in the theory of “Tri-state” is “Tri-state Logic” (“positive | negative | uncertain state”). The ontology of “Tri-state Logic” aims to reveal the meta space-time movement law of things transforming from one form to another, that is, the coupling of time and space in the development of things, and the orientation and evolution of the continuity of things. The mathematical basis of “Tri-state Logic” is knot theory and dynamics theory. The second part of this paper designs a machine-consciousness model framework based on the “Theory of Tri-state” (Tri-state Logic). Its research starting point is the perspective of cognitive dynamics (cognitive psychology + dynamics), which is very different from the research ideas proposed by Minsky's “The Emotion Machine”. At the same time, this paper also tries to answer Turing's questions from different space-time dimensions, and gives an experimental idea of “kindergarten game” by comparing Turing's “imitation game”.

Automation Inner Speech as an Anthropomorphic Feature Affecting Human Trust: Current Issues and Future Directions

This paper aims to discuss the possible role of inner speech in influencing trust in human–automation interaction. Inner speech is an everyday covert inner monolog or dialog with oneself, which is essential for human psychological life and functioning as it is linked to self-regulation and self-awareness. Recently, in the field of machine consciousness, computational models using different forms of robot speech have been developed that make it possible to implement inner speech in robots. As is discussed, robot inner speech could be a new feature affecting human trust by increasing robot transparency and anthropomorphism.

Outline of a Brain Model for Self-Observing Agents

Brain-inspired models for conscious robots should refer to the cellular double structure of the brain, consisting of the neuronal system and the glial system, embodying two ontological realms. Therefore, a purely neurobiological approach to machine consciousness is biased by an ontological fault in exclusively referring to the neuronal system. The brain model for self-observing agents outlined in this paper focuses on the glial-neuronal synaptic units (tripartite synapses). Whereas the neuronal component of the synapse embodies objective subjectivity processing sensory information, the glial component (astrocyte) embodies subjective subjectivity generating subjective behavior (intentions, consciousness) in its interactions with the neuronal part of the synapse. The elementary principle of the implementation of self-observing agents is this: a brain is capable of self-observation, if the concept of intention to observe something and the concept of the observed are located in different places. Based on a formalism of qualitative information processing, the architecture of self-observation is described in increasing complexity, building networks. It is suggested that if a robot brain is equipped with a network of modules for self-observation, the robot may generate subjective perspectives of self-observation indicating self-consciousness.

Artificial Consciousness, Meta-Knowledge, and Physical Omniscience

Previous work [Chrisley & Sloman, 2016, 2017] has argued that a capacity for certain kinds of meta-knowledge is central to modeling consciousness, especially the recalcitrant aspects of qualia, in computational architectures. After a quick review of that work, this paper presents a novel objection to Frank Jackson’s Knowledge Argument (KA) against physicalism, an objection in which such meta-knowledge also plays a central role. It is first shown that the KA’s supposition of a person, Mary, who is physically omniscient, and yet who has not experienced seeing red, is logically inconsistent, due to the existence of epistemic blindspots for Mary. It is then shown that even if one makes the KA consistent by supposing a more limited physical omniscience for Mary, this revised argument is invalid. This demonstration is achieved via the construction of a physical fact (a recursive conditional epistemic blindspot) that Mary cannot know before she experiences seeing red for the first time, but which she can know afterward. After considering and refuting some counter-arguments, the paper closes with a discussion of the implications of this argument for machine consciousness, and vice versa.

Conscious Machines: A Possibility? If So, How?

The scope of the paper is to encourage scientists and engineering to avoid to do what Einstein pointed out as being the hallmark of folly. Machine consciousness scholars must be brave enough to step out of the beaten path. There must be some big recurrent conceptual mistakes that prevent science and technology from addressing machine consciousness.

Understanding and Machine Consciousness

The domain of machine consciousness is a melting pot of computers, robots, neuropsychology, sociology and philosophy. This is both an opportunity and a serious risk of stagnation in entertaining but never-ending discussions that may prove useless concerning the construction of better machines. This paper analyzes this situation, defends an engineering approach to machine consciousness research and proposes a strategy focused on machine understanding to get out of the current impasse.