×

NeurASP

swMATH ID: 43631
Software Authors: Yang, Zhun; Ishay, Adam; Lee, Joohyung
Description: NeurASP is a simple extension of answer set programs by embracing neural networks. By treating the neural network output as the probability distribution over atomic facts in answer set programs, NeurASP provides a simple and effective way to integrate sub-symbolic and symbolic computation. This repository includes examples to show: how NeurASP can make use of pretrained neural networks in symbolic computation and how it can improve the perception accuracy of a neural network by applying symbolic reasoning in answer set programming; and how NeurASP is used to train a neural network better by training with rules so that a neural network not only learns from implicit correlations from the data but also from the explicit complex semantic constraints expressed by ASP rules.
Homepage: https://www.ijcai.org/proceedings/2020/0243.pdf
Source Code:  https://github.com/azreasoners/NeurASP
Dependencies: Python
Related Software: DeepProbLog; ProbLog; Adam; CLEVR; CLEVR dataset; SMProbLog; DL2; NeuroSAT; PRISM; Clingo; ASSAT; Metagol; VQA; TensorLog; InfoGAN; AI2; IMLI; MLIC; GamePad; HOList
Cited in: 13 Documents