Related papers: This looks more like that: Enhancing Self-Explaini…

Pretrained transformer-based Language Models (LMs) are well-known for their ability to achieve significant improvement on NLP tasks, but their black-box nature, which leads to a lack of interpretability, has been a major concern. My…

Layer-wise relevance propagation (LRP) is a widely used and powerful technique to reveal insights into various artificial neural network (ANN) architectures. LRP is often used in the context of image classification. The aim is to…

Part-prototype Networks (ProtoPNets) are concept-based classifiers designed to achieve the same performance as black-box models without compromising transparency. ProtoPNets compute predictions based on similarity to class-specific…

Prototypical part neural networks (ProtoPartNNs), namely PROTOPNET and its derivatives, are an intrinsically interpretable approach to machine learning. Their prototype learning scheme enables intuitive explanations of the form, this…

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…

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…

We present a deformable prototypical part network (Deformable ProtoPNet), an interpretable image classifier that integrates the power of deep learning and the interpretability of case-based reasoning. This model classifies input images by…

Transformer language models are state of the art in a multitude of NLP tasks. Despite these successes, their opaqueness remains problematic. Recent methods aiming to provide interpretability and explainability to black-box models primarily…

Pre-trained Language Models (PLMs) have achieved great success on Machine Reading Comprehension (MRC) over the past few years. Although the general language representation learned from large-scale corpora does benefit MRC, the poor support…

Prototypical-part models are a popular interpretable alternative to black-box deep learning models for computer vision. However, they are difficult to train, with high sensitivity to hyperparameter tuning, inhibiting their application to…

Pre-trained Language Models (PLMs) are trained on large amounts of unlabeled data, yet they exhibit remarkable reasoning skills. However, the trustworthiness challenges posed by these black-box models have become increasingly evident in…

Deep neural networks have achieved remarkable performance in various text-based tasks but often lack interpretability, making them less suitable for applications where transparency is critical. To address this, we propose ProtoLens, a novel…

In this paper, we introduce ProtoPShare, a self-explained method that incorporates the paradigm of prototypical parts to explain its predictions. The main novelty of the ProtoPShare is its ability to efficiently share prototypical parts…

Neural networks are among the most accurate supervised learning methods in use today. However, their opacity makes them difficult to trust in critical applications, especially when conditions in training may differ from those in practice.…

The transparent formulation of explanation methods is essential for elucidating the predictions of neural networks, which are typically black-box models. Layer-wise Relevance Propagation (LRP) is a well-established method that transparently…

One of the major challenges in machine learning nowadays is to provide predictions with not only high accuracy but also user-friendly explanations. Although in recent years we have witnessed increasingly popular use of deep neural networks…

We propose a novel interpretable deep neural network for text classification, called ProtoryNet, based on a new concept of prototype trajectories. Motivated by the prototype theory in modern linguistics, ProtoryNet makes a prediction by…

Despite the recent progress in deep neural networks (DNNs), it remains challenging to explain the predictions made by DNNs. Existing explanation methods for DNNs mainly focus on post-hoc explanations where another explanatory model is…

Today, it is more important than ever before for users to have trust in the models they use. As Machine Learning models fall under increased regulatory scrutiny and begin to see more applications in high-stakes situations, it becomes…

Robotic agents need to understand how to interact with objects in their environment, both autonomously and during human-robot interactions. Affordance detection on 3D point clouds, which identifies object regions that allow specific…