Sign In

Communications of the ACM

ACM TechNews

Recent Research Tackles the Complexity of Self-Awareness

View as: Print Mobile App Share:

Researchers at the Universidad Politecnica de Madrid's School of Computing are using modular neural networks to model cognitive functions related to awareness and time-delay neural networks to model self-awareness. The researchers say their work represents a significant advance in the modeling of awareness and related cognitive functions.

Theories related to informons, an information entity, and holons, autonomous entities that act both as part and as a whole, have been applied to the research. Awareness-associated processes were simulated and influenced the design and development of software models using modular neural networks to develop multi-entity simulators.

The researchers modeled the time dimension of self-awareness using time-delay neural networks, which have shown that the image that each entity has of its qualities in the past or its expectations for the future affect on how it interacts with other entities. Similar to how individuals form groups with common interest and develop a sense of belonging on several levels, artificial entities may interact in a comparable manner to achieve a particular purpose. The research could have applications in building biological models by addressing the problem of awareness through the formulation and computer simulation of artificial models. It also could have applications in artificial intelligence by allowing for the deployment of some of these features in multi-purpose artificial systems, including robots, softbots, and multi-agent systems.

From Universidad Politecnica de Madrid
View Full Article


No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account