English
Related papers

Related papers: Partition of Unity Neural Networks for Interpretab…

200 papers

The output scores of a neural network classifier are converted to probabilities via normalizing over the scores of all competing categories. Computing this partition function, $Z$, is then linear in the number of categories, which is…

Machine Learning · Statistics 2015-08-10 Pushpendre Rastogi , Benjamin Van Durme

Deep learning vision systems excel at pattern recognition yet falter when inputs are noisy or the model must explain its own confidence. Fuzzy inference, with its graded memberships and rule transparency, offers a remedy, while…

Quantum Physics · Physics 2025-06-16 Jianhong Yao , Yangming Guo

Graph neural networks (GNNs) are powerful tools on graph data. However, their predictions are mis-calibrated and lack interpretability, limiting their adoption in critical applications. To address this issue, we propose a new…

Machine Learning · Computer Science 2025-08-26 Lingkai Kong , Haotian Sun , Yuchen Zhuang , Haorui Wang , Wenhao Mu , Chao Zhang

Consider a binary classification problem solved using a feed-forward artificial neural network (ANN). Let the ANN be composed of a ReLU layer and several linear layers (convolution, sum-pooling, or fully connected). We assume the network…

Logic in Computer Science · Computer Science 2024-08-27 Ingo Schmitt

Deep neural networks have demonstrated superior performance in artificial intelligence applications, but the opaqueness of their inner working mechanism is one major drawback in their application. The prevailing unit-based interpretation is…

Computer Vision and Pattern Recognition · Computer Science 2024-02-29 Lei Lyu , Chen Pang , Jihua Wang

Probabilistic Neural Network (PNN) is a feed-forward artificial neural network developed for solving classification problems. This paper proposes a hardware implementation of an approximated PNN (APNN) algorithm in which the conventional…

Emerging Technologies · Computer Science 2018-08-03 Olga Krestinskaya , Alex Pappachen James

Functions are rich in meaning and can be interpreted in a variety of ways. Neural networks were proven to be capable of approximating a large class of functions[1]. In this paper, we propose a new class of neural networks called "Neural…

Machine Learning · Computer Science 2020-01-16 Firat Tuna

Probabilistic Circuits (PCs) are prominent tractable probabilistic models, allowing for a range of exact inferences. This paper focuses on the main algorithm for training PCs, LearnSPN, a gold standard due to its efficiency, performance,…

Machine Learning · Computer Science 2024-03-22 Soroush Ghandi , Benjamin Quost , Cassio de Campos

Combining neural networks with continuous logic and multicriteria decision making tools can reduce the black box nature of neural models. In this study, we show that nilpotent logical systems offer an appropriate mathematical framework for…

Artificial Intelligence · Computer Science 2020-05-01 Orsolya Csiszár , Gábor Csiszár , József Dombi

Deep Neural Networks (DNNs) training can be difficult due to vanishing and exploding gradients during weight optimization through backpropagation. To address this problem, we propose a general class of Hamiltonian DNNs (H-DNNs) that stem…

Machine Learning · Computer Science 2023-01-02 Clara Lucía Galimberti , Luca Furieri , Liang Xu , Giancarlo Ferrari-Trecate

In this paper, we propose the augmented physics-informed neural network (APINN), which adopts soft and trainable domain decomposition and flexible parameter sharing to further improve the extended PINN (XPINN) as well as the vanilla PINN…

Machine Learning · Computer Science 2023-10-03 Zheyuan Hu , Ameya D. Jagtap , George Em Karniadakis , Kenji Kawaguchi

Among interpretable machine learning methods, the class of Generalised Additive Neural Networks (GANNs) is referred to as Self-Explaining Neural Networks (SENN) because of the linear dependence on explicit functions of the inputs. In binary…

Machine Learning · Computer Science 2021-06-17 Paulo J. G. Lisboa , Sandra Ortega-Martorell , Sadie Cashman , Ivan Olier

We discuss probabilistic neural networks with a fixed internal representation as models for machine understanding. Here understanding is intended as mapping data to an already existing representation which encodes an {\em a priori}…

Disordered Systems and Neural Networks · Physics 2023-12-07 Rongrong Xie , Matteo Marsili

The stunning empirical successes of neural networks currently lack rigorous theoretical explanation. What form would such an explanation take, in the face of existing complexity-theoretic lower bounds? A first step might be to show that…

Machine Learning · Computer Science 2017-07-18 Le Song , Santosh Vempala , John Wilmes , Bo Xie

Deep learning models have achieved state-of-the-art performance in many classification tasks. However, most of them cannot provide an interpretation for their classification results. Machine learning models that are interpretable are…

Machine Learning · Computer Science 2021-11-04 Miles Q. Li , Benjamin C. M. Fung , Adel Abusitta

Fine-grained image classification remains challenging due to the large intra-class variance and small inter-class variance. Since the subtle visual differences are only in local regions of discriminative parts among subcategories, part…

Computer Vision and Pattern Recognition · Computer Science 2022-04-01 Runsheng Zhang , jian zhang , Yaping Huang , Qi Zou

We introduce an optimized physics-informed neural network (PINN) trained to solve the problem of identifying and characterizing a surface breaking crack in a metal plate. PINNs are neural networks that can combine data and physics in the…

Machine Learning · Computer Science 2020-05-09 Khemraj Shukla , Patricio Clark Di Leoni , James Blackshire , Daniel Sparkman , George Em Karniadakis

Prevalent semantic segmentation solutions, despite their different network designs (FCN based or attention based) and mask decoding strategies (parametric softmax based or pixel-query based), can be placed in one category, by considering…

Computer Vision and Pattern Recognition · Computer Science 2022-04-05 Tianfei Zhou , Wenguan Wang , Ender Konukoglu , Luc Van Gool

A deep neural network (DNN) with piecewise linear activations can partition the input space into numerous small linear regions, where different linear functions are fitted. It is believed that the number of these regions represents the…

Machine Learning · Computer Science 2020-04-30 Xiao Zhang , Dongrui Wu

One fruitful formulation of Deep Networks (DNs) enabling their theoretical study and providing practical guidelines to practitioners relies on Piecewise Affine Splines. In that realm, a DN's input-mapping is expressed as per-region affine…

Machine Learning · Computer Science 2024-01-23 Randall Balestriero , Yann LeCun