English
Related papers

Related papers: Neural network interpretability with layer-wise re…

200 papers

Deep neural networks (DNN) such as Multi-Layer Perception (MLP) and Convolutional Neural Networks (CNN) represent one of the most established deep learning algorithms. Given the tremendous effects of the number of hidden layers on network…

Image and Video Processing · Electrical Eng. & Systems 2021-11-17 Shihao Shao , Yong Liu , Qinghua Cui

We propose a new interpretability method for neural networks, which is based on a novel mathematico-philosophical theory of reasons. Our method computes a vector for each neuron, called its reasons vector. We then can compute how strongly…

Machine Learning · Computer Science 2025-05-21 Levin Hornischer , Hannes Leitgeb

Convolutional neural networks (CNNs) have achieved superior accuracy in many visual related tasks. However, the inference process through intermediate layers is opaque, making it difficult to interpret such networks or develop trust in…

Computer Vision and Pattern Recognition · Computer Science 2021-10-22 Yael Konforti , Alon Shpigler , Boaz Lernerand Aharon Bar-Hillel

Explaining recommendations enables users to understand whether recommended items are relevant to their needs and has been shown to increase their trust in the system. More generally, if designing explainable machine learning models is key…

Machine Learning · Computer Science 2020-08-27 Darius Afchar , Romain Hennequin

There is strong interest in developing mathematical methods that can be used to understand complex neural networks used in image analysis. In this paper, we introduce techniques from Linear Algebra to model neural network layers as maps…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Rebecca Pattichis , Marios S. Pattichis

Convolutional neural networks (CNNs) have achieved remarkable performance in hyperspectral image (HSI) classification over the last few years. Despite the progress that has been made, rich and informative spectral information of HSI has…

Computer Vision and Pattern Recognition · Computer Science 2024-07-09 Huiling Wang

Saliency map generation techniques are at the forefront of explainable AI literature for a broad range of machine learning applications. Our goal is to question the limits of these approaches on more complex tasks. In this paper we apply…

Machine Learning · Computer Science 2019-07-15 David Tuckey , Krysia Broda , Alessandra Russo

We present an interpretable neural network approach to predicting and understanding politeness in natural language requests. Our models are based on simple convolutional neural networks directly on raw text, avoiding any manual…

Computation and Language · Computer Science 2016-10-11 Malika Aubakirova , Mohit Bansal

Interpretability is crucial to enhance trust in machine learning models for medical diagnostics. However, most state-of-the-art image classifiers based on neural networks are not interpretable. As a result, clinicians often resort to known…

We propose the Tikhonov layer, a graph neural network layer that is interpretable by design: once trained, its learned parameters directly reveal which node features and which aspects of the graph topology were leveraged for prediction. In…

Machine Learning · Computer Science 2026-05-28 Nicolas Tremblay , Benjamin Ricaud , Filippo Maria Bianchi

One significant challenge of exploiting Graph neural networks (GNNs) in real-life scenarios is that they are always treated as black boxes, therefore leading to the requirement of interpretability. To address this, model-level…

Machine Learning · Computer Science 2025-09-22 Xiao Yue , Guangzhi Qu , Lige Gan

Explainable artificial intelligence (XAI) is an important area in the AI community, and interpretability is crucial for building robust and trustworthy AI models. While previous work has explored model-level and instance-level explainable…

Machine Learning · Computer Science 2025-12-05 Xudong Wang , Ziheng Sun , Chris Ding , Jicong Fan

Although traditional symbolic reasoning methods are highly interpretable, their application in knowledge graphs link prediction has been limited due to their computational inefficiency. A new RNNNTP method is proposed in this paper, using a…

Machine Learning · Computer Science 2022-03-15 Yu-hao Wu , Hou-biao Li

Rule-based models offer interpretability but struggle with complex data, while deep neural networks excel in performance yet lack transparency. This work investigates a neuro-symbolic rule learning neural network named RL-Net that learns…

Machine Learning · Computer Science 2025-07-01 Sarah Seifi , Tobias Sukianto , Cecilia Carbonelli , Lorenzo Servadei , Robert Wille

Graph Neural Networks (GNNs) are deep learning models that take graph data as inputs, and they are applied to various tasks such as traffic prediction and molecular property prediction. However, owing to the complexity of the GNNs, it has…

Machine Learning · Computer Science 2021-11-02 Tetsu Kasanishi , Xueting Wang , Toshihiko Yamasaki

Deep ReLU Networks can be decomposed into a collection of linear models, each defined in a region of a partition of the input space. This paper provides three results extending this theory. First, we extend this linear decompositions to…

Machine Learning · Computer Science 2023-05-17 Mattia Jacopo Villani , Peter McBurney

Nonlinear methods such as Deep Neural Networks (DNNs) are the gold standard for various challenging machine learning problems, e.g., image classification, natural language processing or human action recognition. Although these methods…

Machine Learning · Computer Science 2017-11-15 Grégoire Montavon , Sebastian Bach , Alexander Binder , Wojciech Samek , Klaus-Robert Müller

Understanding the inner representation of a neural network helps users improve models. Concept-based methods have become a popular choice for explaining deep neural networks post-hoc because, unlike most other explainable AI techniques,…

Computer Vision and Pattern Recognition · Computer Science 2025-06-09 Aditya Taparia , Som Sagar , Ransalu Senanayake

To equip Convolutional Neural Networks (CNNs) with explainability, it is essential to interpret how opaque models take specific decisions, understand what causes the errors, improve the architecture design, and identify unethical biases in…

Computer Vision and Pattern Recognition · Computer Science 2024-02-23 Mohammad Mahdi Dehshibi , Mona Ashtari-Majlan , Gereziher Adhane , David Masip

Deep neural networks (DNNs) have achieved remarkable success in object detection tasks, but their increasing complexity poses significant challenges for deployment on resource-constrained platforms. While model compression techniques such…

Computer Vision and Pattern Recognition · Computer Science 2026-02-17 Abhinav Shukla , Nachiket Tapas