相关论文: Evaluating Post-hoc Interpretability with Intrinsi…

Deep learning shows promise for medical image analysis but lacks interpretability, hindering adoption in healthcare. Attribution techniques that explain model reasoning may increase trust in deep learning among clinical stakeholders. This…

Despite significant progress in intelligent fault diagnosis (IFD), the lack of interpretability remains a critical barrier to practical industrial applications, driving the growth of interpretability research in IFD. Post-hoc…

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…

Post-hoc interpretability methods play a critical role in explainable artificial intelligence (XAI), as they pinpoint portions of data that a trained deep learning model deemed important to make a decision. However, different post-hoc…

This paper explores interpretability techniques for two of the most successful learning algorithms in medical decision-making literature: deep neural networks and random forests. We applied these algorithms in a real-world medical dataset…

Interpretability is crucial for machine learning algorithms in high-stakes medical applications. However, high-performing neural networks typically cannot explain their predictions. Post-hoc explanation methods provide a way to understand…

Neural networks (NNs), with their powerful nonlinear mapping and end-to-end capabilities, are widely applied in mechanical intelligent fault diagnosis (IFD). However, as typical black-box models, they pose challenges in understanding their…

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

Good quality explanations strengthen the understanding of language models and data. Feature attribution methods, such as Integrated Gradient, are a type of post-hoc explainer that can provide token-level insights. However, explanations on…

Post-hoc explainability methods aim to clarify predictions of black-box machine learning models. However, it is still largely unclear how well users comprehend the provided explanations and whether these increase the users ability to…

The application of deep learning models in medical diagnosis has showcased considerable efficacy in recent years. Nevertheless, a notable limitation involves the inherent lack of explainability during decision-making processes. This study…

Deep neural networks, while powerful for image classification, often operate as "black boxes," complicating the understanding of their decision-making processes. Various explanation methods, particularly those generating saliency maps, aim…

Digital histology images are amenable to the application of convolutional neural network (CNN) for analysis due to the sheer size of pixel data present in them. CNNs are generally used for representation learning from small image patches…

Computer-aided diagnosis (CAD) based on histopathological imaging has progressed rapidly in recent years with the rise of machine learning based methodologies. Traditional approaches consist of training a classification model using features…

The correct interpretation of convolutional models is a hard problem for time series data. While saliency methods promise visual validation of predictions for image and language processing, they fall short when applied to time series. These…

Interpretability methods for deep neural networks mainly focus on the sensitivity of the class score with respect to the original or perturbed input, usually measured using actual or modified gradients. Some methods also use a…

Lung and colon cancer are serious worldwide health challenges that require early and precise identification to reduce mortality risks. However, diagnosis, which is mostly dependent on histopathologists' competence, presents difficulties and…

While Transformers have rapidly gained popularity in various computer vision applications, post-hoc explanations of their internal mechanisms remain largely unexplored. Vision Transformers extract visual information by representing image…

We present a novel methodology for integrating high resolution longitudinal data with the dynamic prediction capabilities of survival models. The aim is two-fold: to improve the predictive power while maintaining interpretability of the…

As AI systems grow more capable, it becomes increasingly important that their decisions remain understandable and aligned with human expectations. A key challenge is the limited interpretability of deep models. Post-hoc methods like GradCAM…