The Grand Challenges and Myths of NeuralSymbolic Computation?

Recurrent Neural Networks - Models, Capacities, and Applications

计算机科学;物理学

Luis C. Lamb

PID  :  81896

学科分类：计算机科学（综合）

来源: CEUR

【 摘 要 】

The construction of computational cognitive models integrating theconnectionist and symbolic paradigms of artificial intelligence is a standing re search issue in the field. The combination of logicbased inference and connec tionist learning systems may lead to the construction of semantically sound com putational cognitive models in artificial intelligence, computer and cognitive sci ences. Over the last decades, results regarding the computation and learning of classical reasoning within neural networks have been promising. Nonetheless, there still remains much do be done. Artificial intelligence, cognitive and com puter science are strongly based on several nonclassical reasoning formalisms, methodologies and logics. In knowledge representation, distributed systems, hard ware design, theorem proving, systems specification and verification classical and nonclassical logics have had a great impact on theory and realworld ap plications. Several challenges for neuralsymbolic computation are pointed out, in particular for classical and nonclassical computation in connectionist systems. We also analyse myths about neuralsymbolic computation and shed new light on them considering recent research advances.