I have not been able to read the original but the abstract sounds very interesting. The
paper is called Self-Consciousness for Artificial Entities using Modular Neural Networks
and here is the abstract. “One of the most puzzling cognitive features is selfconsciousness. A considerable amount of research has been conducted on this
question in different fields like Psychology, Neurobiology and Cognitive
Science. Self-consciousness implies not only self or group recognition, but
also real knowledge of one's own identity. In this paper, a cognitive
architecture of self-consciousness for autonomous artificial entities (holons) is
proposed. This cognitive architecture includes: abstraction, selfrepresentation, other individuals' representation, and action modules. It also
includes a learning process of self-representation by direct (self-experience
based) and observational learning (based on the observation of other
individuals). For model implementation a new approach is taken using
Modular Artificial Neural Networks (MANN) due to their biological
inspiration, modularity and adaptability. We explain the cognitive
architecture that enables dynamic self-representation. For model testing a
multi-holon virtual environment was implemented. We analyse the effect of
holon interaction, focusing on the evolution of the holon's abstract selfrepresentation. Finally, the results are explained and analysed and
conclusions drawn.”
So using computer programs that mimic groups of neurons this Spanish group lead by
Milton Martinez Luaces have produced self-aware programs. ScienceDaily has an item
on this research. (here)
“….This research represents a dual advance in the modelling of awarenessassociated cognitive functions. On the theoretical side, it applies the theory of
informons and holons to awareness structures. An informon is an
information entity. It can take the form of data, news or knowledge. The
term holon refers to autonomous entities that act both as a part and as a
whole.
On the practical side, awareness-associated processes were simulated and
influenced the design and development of software models. To do this,
modular neural networks were used to develop multi-entity simulators. The
networks were used to simulate several scenarios of interaction between their
own potential and that of the systems with which they interact.
In the case of human beings, self-awareness does not imply just an abstract
image of what one is, but also an image of one’s trajectory throughout time.
This research also modelled the time dimension of self-awareness using timedelay neural networks. These networks have shown, in different interaction
scenarios, that the image that each entity has of its qualities in the past or its
expectations for the future has an impact on how it interacts with other
entities. For example, a figure reveals how interaction with other artificial
entities, in this case in a competitive scenario, enables these entities to
develop self-awareness.
In the same way as individuals tend to form groups with common interests
and, as a result, develop a sense of belonging at more than one level, artificial
entities may interact similarly to achieve a particular purpose….”
I hope more detail is available in future.