Guiding Inferences in Connection Tableau by Recurrent Neural Networks

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F20%3A00346116" target="_blank" >RIV/68407700:21730/20:00346116 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.1007/978-3-030-53518-6_23" target="_blank" >https://doi.org/10.1007/978-3-030-53518-6_23</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-030-53518-6_23" target="_blank" >10.1007/978-3-030-53518-6_23</a>

Result language
angličtina
Original language name
Guiding Inferences in Connection Tableau by Recurrent Neural Networks
Original language description
We present a dataset and experiments on applying recurrent neural networks (RNNs) for guiding clause selection in the connection tableau proof calculus. The RNN encodes a sequence of literals from the current branch of the partial proof tree to a hidden vector state; using it, the system selects a clause for extending the proof tree. The training data and learning setup are described, and the results are discussed and compared with state of the art using gradient boosted trees. Additionally, we perform a conjecturing experiment in which the RNN does not just select an existing clause, but completely constructs the next tableau goal.
Czech name
—
Czech description
—

Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project
<a href="/en/project/EF15_003%2F0000466" target="_blank" >EF15_003/0000466: Artificial Intelligence and Reasoning</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2020
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)