paper-with-me

Papers

Deep Learning with Logical Constraints

2022-05-01 · Eleonora Giunchiglia, Mihaela Catalina Stoian, Thomas Lukasiewicz

In recent years, there has been an increasing interest in exploiting logically specified background knowledge in order to obtain neural models (i) with a better performance, (ii) able to learn from less data, and/or (iii) guaranteed to be compliant with the background knowledge itself, e.g., for safety-critical applications. In this survey, we retrace such works and categorize them based on (i) the logical language that they use to express the background knowledge and (ii) the goals that they achieve.

📄 PDF Abstract BibTeX arXiv:2205.00523

Code (0)

등록된 구현이 없습니다.

Tasks

Deep LearningSurvey

Methods 이 논문이 사용한 방법론

Retrace Retrace is an off-policy Q-value estimation algorithm which has guaranteed convergence for a target and behaviour policy $\left(\pi, \beta\right)$. With off-policy rollout for…

Similar Papers 제목 키워드 기반

OptTyper: Probabilistic Type Inference by Optimising Logical and Natural Constraints

2020-04-01 · Irene Vlassi Pandi, Earl T. Barr, Andrew D. Gordon, Charles Sutton

We present a new approach to the type inference problem for dynamic languages. Our goal is to combine \emph{logical} constraints, that is, deterministic information from a type system, with \emph{natural} constraints, th…

Type predictionVocal Bursts Type Prediction

Injecting Logical Constraints into Neural Networks via Straight-Through Estimators

2023-07-10 · Zhun Yang, Joohyung Lee, Chiyoun Park

Injecting discrete logical constraints into neural network learning is one of the main challenges in neuro-symbolic AI. We find that a straight-through-estimator, a method introduced to train binary neural networks, coul…

Learning with Logical Constraints but without Shortcut Satisfaction

2024-03-01 · Zenan Li, Zehua Liu, Yuan YAO, Jingwei Xu 외

Recent studies in neuro-symbolic learning have explored the integration of logical knowledge into deep learning via encoding logical constraints as an additional loss function. However, existing approaches tend to vacuou…

Data-driven learning of symbolic constraints for a log-linear model in a phonological setting

2016-12-01 · COLING 2016 12 · Gabriel Doyle, Roger Levy

We propose a non-parametric Bayesian model for learning and weighting symbolically-defined constraints to populate a log-linear model. The model jointly infers a vector of binary constraint values for each candidate outp…

Machine Translation

Wikidata Constraints on MARS (Extended Technical Report)

2020-08-10 · David L. Martin, Peter F. Patel-Schneider

Wikidata constraints, albeit useful, are represented and processed in an incomplete, ad hoc fashion. Constraint declarations do not fully express their meaning, and thus do not provide a precise, unambiguous basis for co…