Journal of Artificial Intelligence and Consciousness

The quest to understand consciousness, once the purview of philosophers and theologians, is now actively pursued by scientists of many stripes. This paper studies consciousness from the perspective of theoretical computer science. It formalizes the Global Workspace Theory (GWT) originated by the cognitive neuroscientist Bernard Baars and further developed by him, Stanislas Dehaene, and others. Our major contribution lies in the precise formal definition of a Conscious Turing Machine (CTM), also called a Conscious AI. We define the CTM in the spirit of Alan Turing’s simple yet powerful definition of a computer, the Turing Machine (TM). We are not looking for a complex model of the brain nor of cognition but for a simple model of (the admittedly complex concept of) consciousness. After formally defining CTM, we give a formal definition of consciousness in CTM. We later suggest why the CTM has the feeling of consciousness. The reasonableness of the definitions and explanations can be judged by how well they agree with commonly accepted intuitive concepts of human consciousness, the range of related concepts that the model explains easily and naturally, and the extent of its agreement with scientific evidence.

This paper has a critical and a constructive part. The first part formulates a political demand, based on ethical considerations: Until 2050, there should be a global moratorium on synthetic phenomenology, strictly banning all research that directly aims at or knowingly risks the emergence of artificial consciousness on post-biotic carrier systems. The second part lays the first conceptual foundations for an open-ended process with the aim of gradually refining the original moratorium, tying it to an ever more fine-grained, rational, evidence-based, and hopefully ethically convincing set of constraints. The systematic research program defined by this process could lead to an incremental reformulation of the original moratorium. It might result in a moratorium repeal even before 2050, in the continuation of a strict ban beyond the year 2050, or a gradually evolving, more substantial, and ethically refined view of which — if any — kinds of conscious experience we want to implement in AI systems.

Consciousness is key to Artificial General Intelligence. It is currently unclear what is consciousness and we expect that by the time it is understood, there will probably be millions of man-years invested in the development of AI agents. This paper addresses the following question. How should AI agents be engineered from now on, such that when it becomes clear how consciousness and subjective experiences are generated, the effort of endowing AI agents and robots existing at that time with consciousness is minimized. As far as we know this question has not been studied heretofore. The paper proposes a methodology and architecture that are based on evolving Probabilistic Relational Databases, and on stepwise progressive data fusion. The methodology and architecture are independent of what consciousness turns out to be, provided that it can be incorporated into AI agents.

A novel form of neurocomputing allows machines to generate new concepts along with their anticipated consequences, all encoded as chained associative memories. Knowledge is accumulated by the system through direct experience as network chaining topologies form in response to various environmental input patterns. Thereafter, random disturbances to the connections joining these nets promote the formation of alternative chaining topologies representing novel concepts. The resulting ideational chains are then reinforced or weakened as they incorporate nets containing memories of impactful events or things. Such encodings of entities, actions, and relationships as geometric forms composed of artificial neural nets may well suggest how the human brain summarizes and appraises the states of nearly a hundred billion cortical neurons. It may also be the paradigm that allows the scaling of synthetic neural systems to brain-like proportions to achieve sentient artificial general intelligence (SAGI).

A body schema is an agent’s model of its own body that enables it to act on affordances in the environment. This paper presents a body schema system for the Learning Intelligent Decision Agent (LIDA) cognitive architecture. LIDA is a conceptual and computational implementation of Global Workspace Theory, also integrating other theories from neuroscience and psychology. This paper contends that the ‘body schema’ should be split into three separate functions based on the functional role of consciousness in Global Workspace Theory. There is (1) an online model of the agent’s effectors and effector variables (Current Body Schema), (2) a long-term, recognitional storage of embodied capacities for action and affordances (Habitual Body Schema), and (3) “dorsal” stream information feeding directly from early perception to sensorimotor processes (Online Body Schema). This paper then discusses how the LIDA model of the body schema explains several experiments in psychology and ethology.

For humans, phenomenal experiences take up a central role in their daily interaction with the world. In this paper, we argue in favor of shifting phenomenal experiences into the focus of cognitive systems research and development. Instead of aiming to make artificial systems feel in the same way humans do, we focus on the possibilities of engineering capacities that are functionally equivalent to phenomenal experiences. These capacities can provide a different quality of input, enabling a cognitive system to self-evaluate its state in the world more effectively and with more generality than current methods allow. We ground our general argument using the example of the sense of agency. At the same time, we reflect on the broader possibilities and benefits for artificial counterparts to human phenomenal experiences and provide suggestions regarding the implementation of functionally equivalent mechanisms.

Clues from psychology indicate that human cognition are not only based on classical probability theory as explained by Kolmogorov’s axioms but additionally on quantum probability. Quantum probabilities lead to the conclusion that our brain adapted to the Everett many-worlds reality trough the evolutionary process. The Everett many-worlds theory views reality as a many-branched tree in which every possible quantum outcome is realized. In this context, one of the cognitive brain functions is to provide a causally consistent explanation of events to maintain self-identity over time. Causality is related to a meaningful explanation. For impossible explanations, causality does not exist, and the identity of the self breaks. Only in meaningful causal worlds may personal identities exist.

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.