Bridging Logic and Learning: A Neural-Symbolic Approach for Enhanced Reasoning in Neural Models (ASPER) (2312.11651v1)
Abstract: Neural-symbolic learning, an intersection of neural networks and symbolic reasoning, aims to blend neural networks' learning capabilities with symbolic AI's interpretability and reasoning. This paper introduces an approach designed to improve the performance of neural models in learning reasoning tasks. It achieves this by integrating Answer Set Programming (ASP) solvers and domain-specific expertise, which is an approach that diverges from traditional complex neural-symbolic models. In this paper, a shallow artificial neural network (ANN) is specifically trained to solve Sudoku puzzles with minimal training data. The model has a unique loss function that integrates losses calculated using the ASP solver outputs, effectively enhancing its training efficiency. Most notably, the model shows a significant improvement in solving Sudoku puzzles using only 12 puzzles for training and testing without hyperparameter tuning. This advancement indicates that the model's enhanced reasoning capabilities have practical applications, extending well beyond Sudoku puzzles to potentially include a variety of other domains. The code can be found on GitHub: https://github.com/Fadi2200/ASPEN.
- Tensorflow: A system for large-scale machine learning. In 12th {normal-{\{{USENIX}normal-}\}} Symposium on Operating Systems Design and Implementation ({normal-{\{{OSDI}normal-}\}} 16), pages 265–283, 2016.
- Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473, 2014.
- Neural-symbolic learning and reasoning: A survey and interpretation. arXiv preprint arXiv:1711.03902, 2017.
- Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901, 2020.
- Towards synthesizing complex programs from input-output examples. arXiv preprint arXiv:1706.01284, 2017.
- François Chollet et al. Keras. https://keras.io, 2015.
- Human-driven fol explanations of deep learning. In IJCAI, pages 2234–2240, 2020.
- Artur d’Avila Garcez and Luis C Lamb. Neurosymbolic ai: the 3rd wave. arXiv e-prints, pages arXiv–2012, 2020.
- Neural logic machines. arXiv preprint arXiv:1904.11694, 2019.
- Neural-symbolic computing: An effective methodology for principled integration of machine learning and reasoning. arXiv preprint arXiv:1905.06088, 2019.
- Multi-shot asp solving with clingo. Theory and Practice of Logic Programming, 19(1):27–82, 2019.
- The stable model semantics for logic programming. In ICLP/SLP, volume 88, pages 1070–1080. Cambridge, MA, 1988.
- Neuro-symbolic sudoku solver, 2023.
- Scallop: From probabilistic deductive databases to scalable differentiable reasoning. Advances in Neural Information Processing Systems, 34:25134–25145, 2021.
- Generative neurosymbolic machines. Advances in Neural Information Processing Systems, 33:12572–12582, 2020.
- Deepproblog: Neural probabilistic logic programming. Advances in neural information processing systems, 31, 2018.
- The neuro-symbolic concept learner: Interpreting scenes, words, and sentences from natural supervision. arXiv preprint arXiv:1904.12584, 2019.
- G. Marcus and E. Davis. Rebooting ai: Building artificial intelligence we can trust. Pantheon Books, 2019.
- Ilkka Niemelä. Logic programs with stable model semantics as a constraint programming paradigm. Annals of mathematics and Artificial Intelligence, 25:241–273, 1999.
- Recurrent relational networks. In Proceedings of Advances in Neural Information Processing Systems, pages 3368–3378, 2018.
- Kyubyong Park. Can convolutional neural networks crack sudoku puzzles? https://github.com/Kyubyong/sudoku, 2018. Accessed: [Insert Date Here].
- Right for the right concept: Revising neuro-symbolic concepts by interacting with their explanations. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 3619–3629, 2021.
- Satnet: Bridging deep learning and logical reasoning using a differentiable satisfiability solver. In International Conference on Machine Learning, pages 6545–6554. PMLR, 2019.
- Neurasp: Embracing neural networks into answer set programming. arXiv preprint arXiv:2307.07700, 2023.
- Neural-symbolic vqa: Disentangling reasoning from vision and language understanding. Advances in neural information processing systems, 31, 2018.
- Fadi Al Machot (9 papers)