Neural-symbolic cognitive agents : Architecture and theory
conference paper
In real-world applications, the effective integration of learning and reasoning in a cognitive agent model is a difficult task. However, such integration may lead to a better understanding, use and construction of more realistic models. Unfortunately, existing models are either oversimplified or require much processing time, which is unsuitable for online learning and reasoning. Currently, controlled environments like training simulators do not effectively integrate learning and reasoning. In particular, higher-order concepts and cognitive abilities have many unknown temporal relations with the data, making it impossible to represent such relationships by hand. We introduce a novel cognitive agent model and architecture for online learning and reasoning that seeks to effectively represent, learn and reason in complex real-world applications. The agent architecture of the model combines neural learning with symbolic knowledge representation. It is capable of learning new hypotheses from observed data, and infer new beliefs based on these hypotheses. Furthermore, it deals with uncertainty and errors in the data using a Bayesian inference model. The model has successfully been applied in real-time simulation and visual intelligence systems.
Topics
Neural-SymbolicCognitive AgentRestricted Boltzmann Machine (RBM)Temporal LogicCognitive agentNeural-symbolicRestricted boltzmann machine (RBM)Temporal logicAgent architecturesBayesian inference modelCognitive abilityCognitive agentsControlled environmentNeural learningNeural-symbolicObserved dataOnline learningProcessing timeReal time simulationsReal-world applicationRealistic modelRestricted boltzmann machineTemporal relationTraining simulatorVisual intelligenceArchitectureKnowledge representationNetwork architectureProcess designStudentsTemporal logicE-learning
TNO Identifier
462494
Publisher
Imperial College
Source title
Proceedings of ICCSW '11, Imperial College Computing Student Workshop, September 29th–30th 2011, London UK
Editor(s)
Jones, A.V.
Place of publication
London
Pages
10-16
Files
To receive the publication files, please send an e-mail request to TNO Repository.