arXiv:2607. 20277v1 Announce Type: new Abstract: Machine learning models achieve high predictive accuracy in regression tasks, but their deployment in safety-critical and regulated domains requires interpretability.
arXiv:2608. 11768v1 Announce Type: new Abstract: The adaptive neuro-fuzzy inference system (ANFIS) is an interpretable reasoning framework capable of generating explicit IF-THEN fuzzy rules, making it suitable for tasks requiring transparent reasoning.
arXiv:2609.24358v1 Announce Type: new Abstract: Predicting when maritime systems require maintenance can be critical, avoiding hazards and costly consequences. To address this problem, this paper pro...
arXiv:2608. 05859v1 Announce Type: cross Abstract: Interpretable classification often requires more than accurate predictions for real-life deployment: models should be transparent about the evidence behind their decisions and abstain when they cannot decide reliably.
arXiv:2608. 14646v1 Announce Type: cross Abstract: Interpretable representation learning remains a key challenge in modern neural computation, particularly when models are expected not only to perform but also to explain their reasoning.
arXiv:2609. 20194v1 Announce Type: cross Abstract: Triangular membership functions (MFs) are widely used in fuzzy systems because of their interpretability, low parameterization complexity, and strong locality properties.
arXiv:2512. 03578v3 Announce Type: replace-cross Abstract: Time series extrinsic regression (TSER) refers to the task of predicting a continuous target variable from an input time series.
arXiv:2608. 10007v1 Announce Type: cross Abstract: The current state-of-the-art (SOTA) deep randomized neural networks, such as deep Random Vector Functional Link (dRVFL) and ensemble deep RVFL (edRVFL), treat all training samples uniformly, which limits their robustness and effectiveness when applied to real-world datasets containing noise and outliers.
arXiv:2607. 15394v1 Announce Type: new Abstract: Black-box models limit the adoption of artificial intelligence in medicine due to their lack of interpretability and reproducibility.
SymboLLM-FE combines symbolic regression and large language models to automate feature engineering for tabular data. It first extracts mathematically expressive formulas that correlate strongly with the target, then refines them with LLMs to improve interpretability. Experiments on six real‑world datasets and four Kaggle competitions show that SymboLLM‑FE outperforms existing AutoFE methods while reducing the number of costly LLM calls.
The paper introduces the Standard Interpretable Model (SIM), a theoretical framework that derives interpretability symmetries and constraints from first principles, enabling the design of interpretable machine learning methods. SIM allows building models that incorporate these constraints either through optimisation or architecture design, and demonstrates that full expressivity and interpretability can coexist without sacrificing performance. The authors validate the approach on language models, showing that SIM-based models match opaque counterparts while remaining interpretable, and outline how SIM can enhance existing pre‑trained models and guide future research.
arXiv:2610.00391v1 Announce Type: cross Abstract: Synthetic medical tabular data generation has become essential for developing and validating computer-based medical systems (CBMSs) when real clinica...
The paper introduces three algorithms for creating partially interpretable decision trees that can defer complex inputs to a black‑box model. The methods—an exact search extension of the Branches algorithm, a conversion approach applied to standard CART, and a generalized CART that incorporates deferral during tree growth—show comparable performance on many real‑world datasets. In synthetic settings with inhomogeneous black‑box accuracy, the deferral‑aware CART outperforms regular CART and matches exact search, and the approach is also applied to concept bottleneck models to replace neural networks after the bottleneck.