Neurosymbolic AI

Cognitive Aspects of Neurosymbolic Integration

Neurosymbolic Integration: Uniied versus Hybrid Approaches

Since the mid-1980s, researchers have been pursuing the goal of neurosymbolic integration, i.e., the construction of systems capable of both symbolic and neural processing. We distinguish two major avenues toward this goal: the uniied and the hybrid approaches. Whereas the uniied approach claims that full symbol processing functionalities can be achieved via neural networks alone, the hybrid ap...

Interactive Causation: a Neurosymbolic Agent

Interactive Causation Agent (ICA), a novel unsupervised adaptive neurosymbolic model based on a theory of causality (Interactive Causation), is defined, offering an interactive computational approach to problems in the algorithmic computing of interaction. Interactive Causation provides a compatible framework of nonalgorithmic computation and environment, permitting tractable computation of tem...

Neurosymbolic Integration: Cognitive Grounds and Computational Strategies

The ultimate|if implicit|goal of artiicial intelligence (AI) research is to model the full range of human cognitive capabilities. Symbolic AI and connectionism, the major AI paradigms, have each tried|and failed|to attain this goal. In the meantime, the idea has gained ground that this goal might still be within reach if we could harness the respective strengths of these two paradigms in integr...

Neurosymbolic integration: unified versus hybrid approaches

Since the mid-1980s, researchers have been pursuing the goal of neurosymbolic integration, i.e., the construction of systems capable of both symbolic and neural processing. We distinguish two major avenues toward this goal: the uniied and the hybrid approaches. Whereas the uniied approach claims that full symbol processing functionalities can be achieved via neural networks alone, the hybrid ap...