论文信息 - First-order deduction in neural networks - 字舞流文

First-order deduction in neural networks

We show how the algorithm of SLD-resolution for first-order logic programs can be performed in connectionist neural networks. The most significant properties of the resulting neural networks are their finiteness and ability to learn.

Ekaterina Komendantskaya | E. Komendantskaya | Ekaterina Komendantskaya

[1] Krysia Broda,et al. Neural-symbolic learning systems - foundations and applications , 2012, Perspectives in neural computing.

[2] Stephen Grossberg,et al. Embedding fields: A theory of learning with physiological implications , 1969 .

[3] Robert A. Kowalski,et al. Predicate Logic as Programming Language , 1974, IFIP Congress.

[4] J. A. Robinson,et al. A Machine-Oriented Logic Based on the Resolution Principle , 1965, JACM.

[5] Pascal Hitzler,et al. Logic programs and connectionist networks , 2004, J. Appl. Log..

[6] Teuvo Kohonen,et al. Self-organization and associative memory: 3rd edition , 1989 .

[7] Steffen Hölldobler,et al. Approximating the Semantics of Logic Programs by Recurrent Neural Networks , 1999, Applied Intelligence.

[8] Ekaterina Komendantskaya,et al. LEARNING AND DEDUCTION IN NEURAL NETWORKS AND LOGIC , 2007 .

[9] Artur S. d'Avila Garcez,et al. The Connectionist Inductive Learning and Logic Programming System , 1999, Applied Intelligence.

[10] John Wylie Lloyd,et al. Foundations of Logic Programming , 1987, Symbolic Computation.

[11] Steffen Hölldobler,et al. Towards a New Massively Parallel Computational Model for Logic Programming , 1994 .