AGI and Reflexivity
This work addresses foundational aspects of AGI and consciousness, but it is incremental as it builds on existing concepts without presenting new empirical results.
The paper tackles the problem of defining and implementing reflexivity in intelligent systems, proposing that it is conditioned by topological properties of processes and may be implemented through interconnected deep learning modules with recurrence, and suggests an evaluation framework based on these properties.
We define a property of intelligent systems, which we call Reflexivity. In human beings, it is one aspect of consciousness, and an element of deliberation. We propose a conjecture, that this property is conditioned by a topological property of the processes which implement this reflexivity. These processes may be symbolic, or non symbolic e.g. connexionnist. An architecture which implements reflexivity may be based on the interaction of one or several modules of deep learning, which may be specialized or not, and interconnected in a relevant way. A necessary condition of reflexivity is the existence of recurrence in its processes, we will examine in which cases this condition may be sufficient. We will then examine how this topology and this property make possible the expression of a second property, the deliberation. In a final paragraph, we propose an evaluation of intelligent systems, based on the fulfillment of all or some of these properties.