A graph neural network is a deep learning architecture operating on graph-structured data.
While they have achieved impressive results in many application domains, their applicability …

Research on general machine intelligence is concerned with building machines that are
capable of performing a multitude of highly complex tasks in environments as complex as …

Recently, abstract systems theory has been used as a meta-theory for learning theory and
machine learning in order to model learning systems directly as formal, mathematical …

Without a concrete measure of the “complicatedness” of tasks that artificial agents can
reliably perform, assessing progress in AI is difficult. Only by providing evidence of progress …

Engineering design is the process by which humans develop new solutions to problems.
The solutions need not be perfect or even fully understood, what matters is that they provide …

Theories are required for artificial intelligence (AI) to make greater progress. Despite the
development of several AI theories, their use is minimal and their nature is not widely known …

Hybrid Intelligence (HI) attempts to address and solve cognition-intensive tasks by
combining Artificial Intelligence (AI) with human intelligence. Due to the novelty of the HI …

For any agent to effectively learn how to achieve its goals via interaction with environments,
it must have causal reasoning capabilities. Causal reasoning enables an agent to predict …

Engineering design is a problem-solving process that works from a high-level description of
a problem or plan and proceeds to iteratively define an increasingly detailed solution that …

Research on general machine intelligence is concerned with building machines that are
capable of performing a multitude of highly complex tasks in environments as complex as …