Machine learning and logic: a new frontier in artificial intelligence
Machine learning and logic: a new frontier in artificial intelligence
复制标题
DOI：
10.1007/s10703-023-00430-1
复制
发表时间：
2023-06-14
影响因子：
0.8
通讯作者：
Jha，Somesh
中科院分区：
文献类型：
--
作者：
Ganesh，Vijay;Seshia，Sanjit A. A.;Jha，Somesh
机器学习和逻辑推理自诞生以来一直是人工智能（AI）的两大基础支柱，然而，直到最近，这两个领域之间的相互作用一直相对有限。尽管它们各自取得了成功，而且在很大程度上是独立发展的，但新的问题似乎只有通过结合这两个人工智能领域的想法才能解决。这些问题可以概括为：如何使用学习来使逻辑推理和综合/验证引擎更有效和强大，以及在相反的方向上，我们如何使用推理来提高学习的准确性，泛化性和可信度。在这篇观点论文中，我们将重点讨论上述问题，并强调学习和推理交叉点的某些范式趋势。我们在这里的目的不是要全面考察过去学习和推理结合的所有方式。相反，我们专注于某些最近的范例，其中学习和推理之间的反馈回路似乎起着特别重要的作用.具体来说，我们观察到以下三个趋势：第一，学习技巧的运用（特别是强化学习）在排序，选择和初始化证明规则的求解器/证明器;第二，归纳学习和演绎推理的程序合成和验证的上下文中的组合;第三，使用求解器层为机器学习模型提供纠正反馈，以帮助提高其准确性，可推广性，以及相对于部分规范或领域知识的鲁棒性。我们相信，这些范式可能会在未来很长一段时间内对人工智能及其应用产生重大而巨大的影响。
Machine learning and logical reasoning have been the two foundational pillars of Artificial Intelligence (AI) since its inception, and yet, until recently the interactions between these two fields have been relatively limited. Despite their individual success and largely independent development, there are new problems on the horizon that seem solvable only via a combination of ideas from these two fields of AI. These problems can be broadly characterized as follows: how can learning be used to make logical reasoning and synthesis/verification engines more efficient and powerful, and in the reverse direction, how can we use reasoning to improve the accuracy, generalizability, and trustworthiness of learning. In this perspective paper, we address the above-mentioned questions with an emphasis on certain paradigmatic trends at the intersection of learning and reasoning. Our intent here is not to be a comprehensive survey of all the ways in which learning and reasoning have been combined in the past. Rather we focus on certain recent paradigms wherecorrective feedback loopsbetween learning and reasoning seem to play a particularly important role. Specifically, we observe the following three trends: first, the use of learning techniques (especially, reinforcement learning) in sequencing, selecting, and initializing proof rules in solvers/provers; second, combinations of inductive learning and deductive reasoning in the context of program synthesis and verification; and third, the use of solver layers in providing corrective feedback to machine learning models in order to help improve their accuracy, generalizability, and robustness with respect to partial specifications or domain knowledge. We believe that these paradigms are likely to have significant and dramatic impact on AI and its applications for a long time to come.