paper-with-me

홈 › Papers

Comparing Differentiable Logics for Learning Systems: A Research Preview

2023-11-16 · Thomas Flinkow, Barak A. Pearlmutter, Rosemary Monahan

Extensive research on formal verification of machine learning (ML) systems indicates that learning from data alone often fails to capture underlying background knowledge. A variety of verifiers have been developed to ensure that a machine-learnt model satisfies correctness and safety properties, however, these verifiers typically assume a trained network with fixed weights. ML-enabled autonomous systems are required to not only detect incorrect predictions, but should also possess the ability to self-correct, continuously improving and adapting. A promising approach for creating ML models that inherently satisfy constraints is to encode background knowledge as logical constraints that guide the learning process via so-called differentiable logics. In this research preview, we compare and evaluate various logics from the literature in weakly-supervised contexts, presenting our findings and highlighting open problems for future work. Our experimental results are broadly consistent with results reported previously in literature; however, learning with differentiable logics introduces a new hyperparameter that is difficult to tune and has significant influence on the effectiveness of the logics.

📄 PDF Abstract BibTeX arXiv:2311.09809

Code (1)

tflinkow/dl-comparison 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Differentiable Logics for Neural Network Training and Verification

2022-07-14 · Natalia Slusarz, Ekaterina Komendantskaya, Matthew L. Daggitt, Robert Stewart

The rising popularity of neural networks (NNs) in recent years and their increasing prevalence in real-world applications have drawn attention to the importance of their verification. While verification is known to be co…

Formal Logic

Logic of Differentiable Logics: Towards a Uniform Semantics of DL

2023-03-19 · Natalia Ślusarz, Ekaterina Komendantskaya, Matthew L. Daggitt, Robert Stewart 외

Differentiable logics (DL) have recently been proposed as a method of training neural networks to satisfy logical specifications. A DL consists of a syntax in which specifications are stated and an interpretation functio…

Analyzing Differentiable Fuzzy Implications

2020-06-04 · Emile van Krieken, Erman Acar, Frank van Harmelen

Combining symbolic and neural approaches has gained considerable attention in the AI community, as it is often argued that the strengths and weaknesses of these approaches are complementary. One such trend in the literat…

Weakly-supervised Learning

Analyzing Differentiable Fuzzy Logic Operators

2020-02-14 · Emile van Krieken, Erman Acar, Frank van Harmelen

The AI community is increasingly putting its attention towards combining symbolic and neural approaches, as it is often argued that the strengths and weaknesses of these approaches are complementary. One recent trend in …

Weakly-supervised Learning

Deep Differentiable Logic Gate Networks

2022-10-15 · Felix Petersen, Christian Borgelt, Hilde Kuehne, Oliver Deussen

Recently, research has increasingly focused on developing efficient neural network architectures. In this work, we explore logic gate networks for machine learning tasks by learning combinations of logic gates. These net…

CPUEfficient Neural Network