Unification neural networks: unification by error-correction learning

作者：Komendantskaya Ekaterina^*

来源：Logic Journal of the IGPL, 2011, 19(6): 821-847.

DOI：10.1093/jigpal/jzq012

• Unification
• Neuro-Symbolic Networks
• Neural Network Learning
• Error-correction Learning
• Hybrid Networks
• Connectionism

We show that the conventional first-order algorithm of unification can be simulated by finite artificial neural networks with one layer of neurons. In these unification neural networks, the unification algorithm is performed by error-correction learning. Each time-step of adaptation of the network corresponds to a single iteration of the unification algorithm. We present this result together with the library of learning functions and examples fully formalised in MATLAB Neural Network Toolbox.

• 出版日期2011-12