26 papers · ranked by Valyu relevance
Johan Pena-Campos, Diego Patino, Carlos Ocampo-Martinez, Julio C. Ramos-Fernández + 2 more
Black-box models, particularly Support Vector Machines (SVM), are widely employed for identifying dynamic systems due to their high predictive accuracy; however, their inherent lack of transparency hinders the understanding of how individual input variables contribute to the system output. Consequently, retrieving…
Jiaxing Li, Wenkai Zhou, Shilei Jiang, Tianhao Zhang + 3 more
Predicting student performance is essential for making informed teaching decisions, customizing learning, and ensuring educational equity. When developing student performance prediction models, it is crucial to provide high prediction accuracy, a clear and logical prediction process, as well as easily understandable…
Zerui Zhang, Hongbo Zhao, Li Dong, Lin Luo + 3 more
This study focuses on the interpretability of diabetic retinopathy classification models. Seven widely used interpretability methods-Gradient, SmoothGrad, Integrated Gradients, SHAP, DeepLIFT, Grad-CAM++, and ScoreCAM-are applied to assess the interpretability of four representative deep learning architectures, VGG…
Rikab Gambhir, Luisa Lucie-Smith, Jesse Thaler
We review the concepts of interpretability and explainability as they apply to machine learning in physics. We define interpretability as concerning the structural transparency of a model (the ability to understand or approximate its inner workings) and explainability as concerning the scientific content of a model…
Riccardo Guidotti, Martina Cinquini, Marta Marchiori Manerba, Mattia Setzu + 1 more
Interpretable-by-design models are crucial for fostering trust, accountability, and safe adoption of automated decision-making models in real-world applications. In this paper we formalize the ground for the MIMOSA (Mining Interpretable Models explOiting Sophisticated Algorithms) framework, a comprehensive methodology…
A H M Osama Haque, Abdullah Al Fahad, M Sohel Rahman, Md Abul Hassan Samee
Alzheimer’s Disease remains a major public health challenge, requiring insights into feature interactions and temporal trends of feature importance. Community-wide data science competitions such as the TADPOLE Challenge provide platforms to benchmark predictive models using ADNI datasets. While top-performing models…
Mattia Billa, Giovanni Orlandi, Veronica Guidetti, Federica Mandreoli
In recent years, machine learning models have seen widespread adoption across a broad range of sectors, including high-stakes domains such as healthcare, finance, and law. This growing reliance has raised increasing concerns regarding model interpretability and accountability, particularly as legal and regulatory…
Thanh Hoa Vo, Nguyen Quoc Khanh Le
The integration of multi-omics data has become increasingly important in advancing precision medicine and systems biology. However, the reliability and trustworthiness of artificial intelligence (AI) models applied to such data remain critical concerns. This review examines the evolution and current landscape of…
Jianyu Yang, Shaun Mahony
Interpreting genomics deep learning models remains challenging. Existing feature attribution methods largely focus on scoring individual bases or extracting global DNA motifs from one-hot encoded inputs, leaving them unable to assess broader genomic features such as chromatin accessibility or sequence annotations.…
David Martínez-Enguita, Thomas Hillerton, Julia Åkesson, Maria Lerm + 1 more
Genome-scale DNA methylation (DNAm) profiles capture organismal physiology, but most predictive models lack transparency and multi-level applicability. Here we develop an explainable framework that quantifies respiratory, cardiovascular, and metabolic status as bounded health scores (0–1) derived from sex-specific…
Pietro Barbiero, Giovanni De Felice, Mateo Espinosa Zarlenga, Francesco Giannini + 4 more
As Artificial Intelligence models grow in complexity, interpretability has become an indispensable tool for understanding, debugging, and controlling their computations. However, interpretability lacks general theories to deductively design interpretable methods. This gap between theories and methods results in a…
Ward Gauderis, Thomas Dooms, Steven T. Holmer, Kola Ayonrinde + 1 more
Mechanistic interpretability aims to explain neural model behaviour by reverse-engineering learned computational structure into human-understandable components. Without a formal framework, however, mechanistic explanations cannot be objectively verified, compared, or composed. We introduce compositional…
Lasse Bohlen, Julian Rosenberger, Nico Hambauer, Daniel Zähringer + 3 more
The application of machine learning (ML) models in healthcare management offers high potential. In particular, resource allocation and operational decision-making in intensive care units (ICUs) can benefit from ML predictions, leading to improvements in patient outcomes and operational efficiency. However, the…
Authors not listed
Supervised deep learning has become a standard approach to deliver competitive predictive tools that allow relating the structure of molecules and their physicochemical features to properties such as binding to protein targets, performance as electronic materials, and reactivity. However, efforts to understand how…
M.A. Lieftinck, T. Verlaan, M.J.T. Reinders
Deep Neural Networks (DNNs) are renowned for their high accuracy and versatility, which has led to their application in many fields of research, including biology. However, this accuracy often comes at the expense of interpretability, making it challenging to reason about the inner workings of most DNNs. Particularly…
Mohamed Ebraheem, Jamie Toghranegar, Yael Bensoussan, John Michael Templeton + 1 more
Background Driven by recent advances in artificial intelligence (AI), particularly in medicine, audio-based voice and speech biomarkers are increasingly investigated for various medical applications as a complementary or even alternative modality to traditional medical devices. The adoption of deep learning techniques…
Authors not listed
Machine learning (ML) models have been widely used as efficient surrogates to predict adsorption in metal-organic frameworks (MOFs), for gas storage, chemical separations, and catalysis applications. The “black box” nature of these ML models, however, remains a significant barrier between predictions and the design of…
Binbin Yong, Haoran Pei, Jun Shen, Haoran Li + 2 more
Adaptive Neuro-Fuzzy Inference System (ANFIS) was designed to combine the learning capabilities of neural network with the reasoning transparency of fuzzy logic. However, conventional ANFIS architectures suffer from structural complexity, where the product-based inference mechanism causes an exponential explosion of…
Authors not listed
High-entropy layered double hydroxides (HE-LDHs) have shown great potential in oxygen evolution reaction (OER) catalysis due to their tunable compositions and electronic structures. However, the synergistic effects between multiple vacancies, such as metal and oxygen vacancies, remain poorly understood and challenging…
Dennis Gankin, Pedro Beltrao
Biologically inspired neural networks (BINNs) embed pathway, ontology, or protein-interaction structure directly into neural networks, promising interpretable disease prediction where hidden nodes map to named biological entities. Yet BINNs have been hard to train at biobank scale, and the reliability of their…
Ziba Jabbar Zare, Ulrich Aïvodji, Julien Ferry, Thibaut Vidal
Hybrid interpretable models combine a transparent component with a black-box model by assigning some examples to the former and deferring the rest to the latter. While this design enables flexible tradeoffs between accuracy and interpretability, it also raises a distinct procedural fairness concern: some demographic…
Authors not listed
Artificial intelligence (AI) is reshaping chemical engineering. Still, its role in safety-critical operations is limited because we rarely see tools that link physical models with data-driven methods. This study brings together three elements: physics-constrained neural networks, uncertainty quantification, and a…
Authors not listed
Accurate extrapolation in data-scarce scientific systems remains a central challenge for machine intelligence. In microbial bioprocessing, kinetic parameters change non-monotonically with reactor volume due to interacting hydrodynamic, oxygen-transfer, and mixing effects, rendering classical empirical scaling laws…
Pin Lyu, Lawrence Fulton
Invasive species management demands predictive models that balance accuracy with ecological interpretability. Traditional approaches often fail to capture complex environmental interactions. We evaluated hybrid frameworks integrating biological and machine learning models for rainbow trout (Oncorhynchus mykiss) growth…
Authors not listed
Predicting drug-induced toxicity remains a central challenge in computational toxicology, particularly for organ-specific adverse effects that arise from diverse structural, biochemical, and mechanistic origins. Existing deep learning models excel at pattern recognition but often lack mechanistic interpretability…
Authors not listed
Pharmacophores are widely used to describe protein-ligand interactions, and the Grids of Pharmacophore Interaction Fields (GRAIL) method extends this concept by representing binding pockets as interpretable sets of interaction type-specific pharmacophoric maps. In this work, we propose a hybrid framework for binding…