Guillame-Bert, M., Broda, K. & Garcez, A. d'Avila (2010). First-order logic learning in artificial neural networks. International Joint Conference on Neural Networks (IJCNN 2010), doi: 10.1109/IJCNN.2010.5596491
Download (343kB) | Preview
Artificial Neural Networks have previously been applied in neuro-symbolic learning to learn ground logic program rules. However, there are few results of learning relations using neuro-symbolic learning. This paper presents the system PAN, which can learn relations. The inputs to PAN are one or more atoms, representing the conditions of a logic rule, and the output is the conclusion of the rule. The symbolic inputs may include functional terms of arbitrary depth and arity, and the output may include terms constructed from the input functors. Symbolic inputs are encoded as an integer using an invertible encoding function, which is used in reverse to extract the output terms. The main advance of this system is a convention to allow construction of Artificial Neural Networks able to learn rules with the same power of expression as first order definite clauses. The system is tested on three examples and the results are discussed.
|Additional Information:||Presented at the 2010 International Joint Conference on Neural Networks, Barcelona, Spain, 18 - 23 July 2010.|
|Uncontrolled Keywords:||artificial neural networks, cognition, computer architecture, encoding, indexes, neurons, training|
|Subjects:||Q Science > QA Mathematics > QA75 Electronic computers. Computer science|
|Divisions:||School of Informatics > Department of Computing|
Actions (login required)