English
Related papers

Related papers: Spectral Identifiability for Interpretable Probe G…

200 papers

A typical 2D-to-3D pipeline takes multi-view images as input, where a Vision Foundation Model (VFM) extracts features that are spatially upsampled to dense representations for 3D reconstruction. If dense features across views preserve…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Ling Xiao , Yuliang Xiu , Yue Chen , Guoming Wang , Toshihiko Yamasaki

Conformal Prediction (CP) is a popular method for uncertainty quantification with machine learning models. While conformal prediction provides probabilistic guarantees regarding the coverage of the true label, these guarantees are agnostic…

Machine Learning · Computer Science 2025-10-21 Aditya T. Vadlamani , Anutam Srinivasan , Pranav Maneriker , Ali Payani , Srinivasan Parthasarathy

Informed learning is an emerging field in machine learning that aims to compensate for insufficient data with prior knowledge. Shape knowledge covers many types of prior knowledge concerning the relationship of a function's output with…

Optimization and Control · Mathematics 2024-09-26 Miltiadis Poursanidis , Patrick Link , Jochen Schmid , Uwe Teicher

Graph filter design is central to spectral collaborative filtering, yet most existing methods rely on manually tuned hyperparameters rather than fully learnable filters. We show that this challenge stems from a bias in traditional…

Information Retrieval · Computer Science 2026-04-27 Yunhang He , Cong Xu , Zhangchi Zhu , Hongzhi Yin , Wei Zhang

Wave steepness is a key geometric variable for describing breaking occurrence and its consequences, including energy dissipation and air entrainment. Using three laboratory campaigns under varying spectral conditions and co-flowing wind…

Fluid Dynamics · Physics 2026-05-29 Rui Cao , Enrique M. Padilla , Xu Chen , Adrian H. Callaghan

The Topological Signal Processing (TSP) framework has been recently developed to analyze signals defined over simplicial complexes, i.e. topological spaces represented by finite sets of elements that are closed under inclusion of subsets…

Signal Processing · Electrical Eng. & Systems 2021-12-14 Stefania Sardellitti , Sergio Barbarossa , Lucia Testa

Electromagnetic Inverse Scattering Problems (EISP) seek to reconstruct relative permittivity from scattered fields and are fundamental to applications like medical imaging. This inverse process is inherently ill-posed and highly nonlinear,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Yizhe Cheng , Chunxun Tian , Haoru Wang , Wentao Zhu , Xiaoxuan Ma , Yizhou Wang

Detecting the High impedance fault (HIF) in distribution systems plays an important role in power utilization safety. However, many HIFs are challenging to be identified due to their low currents and diverse characteristics. In particular,…

Systems and Control · Electrical Eng. & Systems 2020-04-14 Mingjie Wei , Weisheng Liu , Hengxu Zhang , Fang Shi , Weijiang Chen

Reachability analysis has been a prominent way to provide safety guarantees for neurally controlled autonomous systems, but its direct application to neural perception components is infeasible due to imperfect or intractable perception…

Systems and Control · Electrical Eng. & Systems 2026-04-27 Yuang Geng , Thomas Waite , Trevor Turnquist , Radoslav Ivanov , Ivan Ruchkin

Understanding why a model makes a certain prediction can be as crucial as the prediction's accuracy in many applications. However, the highest accuracy for large modern datasets is often achieved by complex models that even experts struggle…

Artificial Intelligence · Computer Science 2017-11-28 Scott Lundberg , Su-In Lee

In clinical applications, the utility of segmentation models is often based on the accuracy of derived downstream metrics such as organ size, rather than by the pixel-level accuracy of the segmentation masks themselves. Thus, uncertainty…

Image and Video Processing · Electrical Eng. & Systems 2026-03-03 Matt Y. Cheung , Ashok Veeraraghavan , Guha Balakrishnan

Spectral envelope is one of the most important features that characterize the timbre of an instrument sound. However, it is difficult to use spectral information in the framework of conventional spectrogram decomposition methods. We…

Sound · Computer Science 2018-01-15 Jeongsoo Park , Jaeyoung Shin , Kyogu Lee

Researchers develop models to explain the unknowns. These models typically involve parameters that capture tangible quantities, the estimation of which is desired. Parameter identifiability investigates the recoverability of the unknown…

Optimization and Control · Mathematics 2024-07-01 Anuththara Sarathchandra , Azadeh Aghaeeyan , Pouria Ramazi

As AI systems are used in high-stakes applications, ensuring interpretability is crucial. Mechanistic Interpretability (MI) aims to reverse-engineer neural networks by extracting human-understandable algorithms to explain their behavior.…

Machine Learning · Computer Science 2025-03-03 Maxime Méloux , Silviu Maniu , François Portet , Maxime Peyrard

Predictive inference requires balancing statistical accuracy against informational complexity, yet the choice of complexity measure is usually imposed rather than derived. We treat econometric objects as predictive rules, mappings from…

Statistics Theory · Mathematics 2026-02-16 Nicholas G. Polson , Daniel Zantedeschi

Linear regression studies the problem of estimating a model parameter $\beta^* \in \mathbb{R}^p$, from $n$ observations $\{(y_i,\mathbf{x}_i)\}_{i=1}^n$ from linear model $y_i = \langle \mathbf{x}_i,\beta^* \rangle + \epsilon_i$. We…

Machine Learning · Statistics 2015-05-14 Xinyang Yi , Zhaoran Wang , Constantine Caramanis , Han Liu

Graph neural networks have demonstrated remarkable success in predicting molecular properties by leveraging the rich structural information encoded in molecular graphs. However, their black-box nature reduces interpretability, which limits…

Machine Learning · Computer Science 2025-08-22 Sebastian Musiał , Bartosz Zieliński , Tomasz Danel

Probes are small networks that predict properties of underlying data from embeddings, and they provide a targeted, effective way to illuminate the information contained in embeddings. While analysis through the use of probes has become…

Part-prototype models are explainable-by-design image classifiers, and a promising alternative to black box AI. This paper explores the applicability and potential of interpretable machine learning, in particular PIP-Net, for automated…

Computer Vision and Pattern Recognition · Computer Science 2023-09-12 Meike Nauta , Johannes H. Hegeman , Jeroen Geerdink , Jörg Schlötterer , Maurice van Keulen , Christin Seifert

This paper explores the intricate relationship between interpretability and robustness in deep learning models. Despite their remarkable performance across various tasks, deep learning models often exhibit critical vulnerabilities,…

Machine Learning · Computer Science 2024-12-30 Navid Nayyem , Abdullah Rakin , Longwei Wang