Learning Logic Programs Using Neural Networks by Exploiting Symbolic Invariance
Learning Logic Programs Using Neural Networks by Exploiting Symbolic Invariance
复制标题
利用符号不变性使用神经网络学习逻辑程序
DOI:
10.1007/978-3-030-97454-1_15
复制
发表时间:
2022
期刊:
影响因子:
--
通讯作者:
Katsumi Inoue
中科院分区:
文献类型:
--
作者:
Yin Jun Phua;Katsumi Inoue
Learning from Interpretation Transition (LFIT) is an unsupervised learning algorithm which learns the dynamics just by observing state transitions. LFIT algorithms have mainly been implemented in the symbolic method, but they are not robust to noisy or missing data. Recently, research works combining logical operations with neural networks are receiving a lot of attention, with most works taking an extraction based approach where a single neural network model is trained to solve the problem, followed by extracting a logic model from the neural network model. However most research work suffer from the combinatorial explosion problem when trying to scale up to solve larger problems. In particular a lot of the invariance that hold in the symbolic world are not getting utilized in the neural network field. In this work, we present a model that exploits symbolic invariance in our problem. We show that our model is able to scale up to larger tasks than previous work.
影响因子:
5.7
作者:
Ribeiro T;Magnin M;Inoue K;Sakama C
通讯作者:
Sakama C
DOI:
--
发表时间:
2011
期刊:
影响因子:
--
作者:
石井明男;尾方成信;君塚肇
通讯作者:
君塚肇
DOI:
--
发表时间:
2019
期刊:
影响因子:
--
作者:
T. Rintala
通讯作者:
T. Rintala