paper-with-me

Papers

Towards Fully Interpretable Deep Neural Networks: Are We There Yet?

2021-06-24 · Sandareka Wickramanayake, Wynne Hsu, Mong Li Lee

Despite the remarkable performance, Deep Neural Networks (DNNs) behave as black-boxes hindering user trust in Artificial Intelligence (AI) systems. Research on opening black-box DNN can be broadly categorized into post-hoc methods and inherently interpretable DNNs. While many surveys have been conducted on post-hoc interpretation methods, little effort is devoted to inherently interpretable DNNs. This paper provides a review of existing methods to develop DNNs with intrinsic interpretability, with a focus on Convolutional Neural Networks (CNNs). The aim is to understand the current progress towards fully interpretable DNNs that can cater to different interpretation requirements. Finally, we identify gaps in current work and suggest potential research directions.

📄 PDF Abstract BibTeX arXiv:2106.13164

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Residualized Similarity for Faithfully Explainable Authorship Verification

2025-10-06 · Peter Zeng, Pegah Alipoormolabashi, Jihu Mun, Gourab Dey 외 arxiv

Responsible use of Authorship Verification (AV) systems not only requires high accuracy but also interpretable solutions. More importantly, for systems to be used to make decisions with real-world consequences requires t…

Structural Neural Additive Models: Enhanced Interpretable Machine Learning

2023-02-18 · Mattias Luber, Anton Thielmann, Benjamin Säfken

Deep neural networks (DNNs) have shown exceptional performances in a wide range of tasks and have become the go-to method for problems requiring high-level predictive power. There has been extensive research on how DNNs …

Additive modelsInterpretable Machine Learning

FocusLearn: Fully-Interpretable, High-Performance Modular Neural Networks for Time Series

2023-11-28 · Qiqi Su, Christos Kloukinas, Artur d'Avila Garcez

Multivariate time series have many applications, from healthcare and meteorology to life science. Although deep learning models have shown excellent predictive performance for time series, they have been criticised for b…

Additive modelsfeature selectionTime SeriesTime Series Forecasting+1

A Hybrid Fully Convolutional CNN-Transformer Model for Inherently Interpretable Medical Image Classification

2025-04-11 · Kerol Djoumessi, Samuel Ofosu Mensah, Philipp Berens

In many medical imaging tasks, convolutional neural networks (CNNs) efficiently extract local features hierarchically. More recently, vision transformers (ViTs) have gained popularity, using self-attention mechanisms to …

image-classificationImage ClassificationMedical Image Classification

Variational pSOM: Deep Probabilistic Clustering with Self-Organizing Maps

2019-09-25 · Laura Manduchi, Matthias Hüser, Gunnar Rätsch, Vincent Fortuin

Generating visualizations and interpretations from high-dimensional data is a common problem in many fields. Two key approaches for tackling this problem are clustering and representation learning. There are very perfor…

ClusteringDeep ClusteringRepresentation LearningTime Series+1