Related papers: Semantic Prototypes: Enhancing Transparency Withou…

In this paper we propose a simple yet powerful method for learning representations in supervised learning scenarios where each original input datapoint is described by a set of vectors and their associated outputs may be given by soft…

We introduce Prototype Generation, a stricter and more robust form of feature visualisation for model-agnostic, data-independent interpretability of image classification models. We demonstrate its ability to generate inputs that result in…

The field of machine learning has seen tremendous progress in recent years, with deep learning models delivering exceptional performance across a range of tasks. However, these models often come at the cost of interpretability, as they…

Modern machine learning models are opaque, and as a result there is a burgeoning academic subfield on methods that explain these models' behavior. However, what is the precise goal of providing such explanations, and how can we demonstrate…

Artificial intelligence (AI) provides many opportunities to improve private and public life. Discovering patterns and structures in large troves of data in an automated manner is a core component of data science, and currently drives…

Sub-symbolic artificial intelligence methods dominate the fields of environment-type classification and Simultaneous Localisation and Mapping. However, a significant area overlooked within these fields is solution transparency for the…

We introduce ProtoSeg, a novel model for interpretable semantic image segmentation, which constructs its predictions using similar patches from the training set. To achieve accuracy comparable to baseline methods, we adapt the mechanism of…

Prior works have demonstrated that implicit representations trained only for reconstruction tasks typically generate encodings that are not useful for semantic tasks. In this work, we propose a method that contextualises the encodings of…

Prototype-based explanations offer an intuitive, example-based approach to support the interpretability of machine learning black box classifiers but often lack feature-level granularity. We introduce a framework that integrates feature…

Foundation models (FMs), including large language models, have become increasingly popular due to their wide-ranging applicability and ability to understand human-like semantics. While previous research has explored the use of FMs in…

Neurosymbolic approaches can add robustness to opaque neural systems by incorporating explainable symbolic representations. However, previous approaches have not used formal logic to contextualize queries to and validate outputs of large…

Deep time series models continue to improve predictive performance, yet their deployment remains limited by their black-box nature. In response, existing interpretability approaches in the field keep focusing on explaining the internal…

Embeddings have become a pivotal means to represent complex, multi-faceted information about entities, concepts, and relationships in a condensed and useful format. Nevertheless, they often preclude direct interpretation. While downstream…

Psychological scale refinement traditionally relies on response-based methods such as factor analysis, item response theory, and network psychometrics to optimize item composition. Although rigorous, these approaches require large samples…

Part-prototype networks have recently become methods of interest as an interpretable alternative to many of the current black-box image classifiers. However, the interpretability of these methods from the perspective of human users has not…

We present a generalizable classification approach that leverages Large Language Models (LLMs) to facilitate the detection of implicitly encoded social meaning in conversations. We design a multi-faceted prompt to extract a textual…

We propose a new fast fully unsupervised method to discover semantic patterns. Our algorithm is able to hierarchically find visual categories and produce a segmentation mask where previous methods fail. Through the modeling of what is a…

Commonsense knowledge is paramount to enable intelligent systems. Typically, it is characterized as being implicit and ambiguous, hindering thereby the automation of its acquisition. To address these challenges, this paper presents…

Embedding is a common technique for analyzing multi-dimensional data. However, the embedding projection cannot always form significant and interpretable visual structures that foreshadow underlying data patterns. We propose an approach that…

Identification of disease subtypes and corresponding biomarkers can substantially improve clinical diagnosis and treatment selection. Discovering these subtypes in noisy, high dimensional biomedical data is often impossible for humans and…