Augmenting Human Selves Through Artificial Agents - Lessons From the Brain

Abstract

Much of current artificial intelligence (AI) and the drive toward artificial general intelligence (AGI) focuses on developing machines for functional tasks that humans accomplish. These may be narrowly specified tasks as in AI, or more general tasks as in AGI - but typically these tasks do not target higher-level human cognitive abilities, such as consciousness or morality; these are left to the realm of so-called "strong AI" or "artificial consciousness." In this paper, we focus on how a machine can augment humans rather than do what they do, and we extend this beyond AGI-style tasks to augmenting peculiarly personal human capacities, such as wellbeing and morality. We base this proposal on associating such capacities with the "self," which we define as the "environment-agent nexus"; namely, a fine-tuned interaction of brain with environment in all its relevant variables. We consider richly adaptive architectures that have the potential to implement this interaction by taking lessons from the brain. In particular, we suggest conjoining the free energy principle (FEP) with the dynamic temporo-spatial (TSD) view of neuro-mental processes. Our proposed integration of FEP and TSD - in the implementation of artificial agents - offers a novel, expressive, and explainable way for artificial agents to adapt to different environmental contexts. The targeted applications are broad: from adaptive intelligence augmenting agents (IA's) that assist psychiatric self-regulation to environmental disaster prediction and personal assistants. This reflects the central role of the mind and moral decision-making in most of what we do as humans.

Keywords: agent-environment interaction; free energy principle; free energy principle and active inference (FEP-AI) framework; hierarchical learning; human self; intelligence augmentation (IA); spatio – temporal dynamics.

FIGURE 1

By minimizing free energy, brain and environment align as seen with the maximization of the joint distribution of the brain’s sensory states (_s) and hidden states of the environment (_ψ) while simultaneously ensuring that the representation of the environment in the brain is maximally entropic (entropy term). Currently the theory has considered neurobiological implementations of this gradient flows – resulting in testable imaging and electrophysiological predictions. With augmentation the goal may be to facilitate extended environmental states (lower left blue panel) that are not readily accommodated in neural states currently but could be accommodated in an artificial agent with extended “sensory” inputs.

FIGURE 2

The schema shows typical core-periphery organization with high connectivity/relationship (lines between dots) among the nodes or members (dots) of the core as well as low connectivity/relationship among the nodes of the periphery and between core and periphery nodes.

FIGURE 3

The figures show the intrinsic neural timescales in the human brain calculated by autocorrelation window (ACW) in human brain data from Human Connectome data set (MEG). (A) Distribution of the duration of intrinsic neural timescales duration throughout the brain and its different regions (red: longer duration of ACW). (B) Decrease in autocorrelation (y-axis) of neural activity over time (x-axis) in different networks (different lines) with demarcation at 50% (ACW) (vertical lines). (C) Values of ACW (y-axis) for the different networks (x-axis). (D) Schematic depiction of core-periphery organization with the color shading of the nodes reflecting the length of intrinsic neural timescales (more dark = longer timescales, more light = shorter timescales).

FIGURE 4

The figure depicts schematically the connection/relationship or alignment between different persons (magenta lines) with one exception as that person (on the right with red circle) is isolated from the others, being unable to connect or relate (A). Improvement of that person’s alignment to others is possible by using the kind of adaptive models (upper right corner) we here suggest – this breaks the person’s isolation allowing them to connect and relate to others (red lines) (B).