Related papers: ProtoVAE: A Trustworthy Self-Explainable Prototypi…
Explainable AI (XAI) is essential for understanding machine learning (ML) decision-making and ensuring model trustworthiness in scientific applications. Prototype-based XAI methods offer an intrinsically interpretable alternative to…
To achieve high-levels of autonomy, modern robots require the ability to detect and recover from anomalies and failures with minimal human supervision. Multi-modal sensor signals could provide more information for such anomaly detection…
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…
Recently, autoencoders (AEs) have gained interest for creating parametric and invertible projections of multidimensional data. Parametric projections make it possible to embed new, unseen samples without recalculating the entire projection,…
Ensembles of decision trees perform well on many problems, but are not interpretable. In contrast to existing approaches in interpretability that focus on explaining relationships between features and predictions, we propose an alternative…
Variational Autoencoders (VAEs) are well-established as a principled approach to probabilistic unsupervised learning with neural networks. Typically, an encoder network defines the parameters of a Gaussian distributed latent space from…
Variational autoencoders (VAEs) employ Bayesian inference to interpret sensory inputs, mirroring processes that occur in primate vision across both ventral (Higgins et al., 2021) and dorsal (Vafaii et al., 2023) pathways. Despite their…
Learning interpretable representations of data remains a central challenge in deep learning. When training a deep generative model, the observed data are often associated with certain categorical labels, and, in parallel with learning to…
Interpretability is essential for user trust in real-world anomaly detection applications. However, deep learning models, despite their strong performance, often lack transparency. In this work, we study the interpretability of…
Instance-based interpretation methods have been widely studied for supervised learning methods as they help explain how black box neural networks predict. However, instance-based interpretations remain ill-understood in the context of…
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…
Finding an interpretable non-redundant representation of real-world data is one of the key problems in Machine Learning. Biological neural networks are known to solve this problem quite well in unsupervised manner, yet unsupervised…
Variational Autoencoders (VAEs) provide a theoretically-backed and popular framework for deep generative models. However, learning a VAE from data poses still unanswered theoretical questions and considerable practical challenges. In this…
Due to the sensitive nature of medicine, it is particularly important and highly demanded that AI methods are explainable. This need has been recognised and there is great research interest in xAI solutions with medical applications.…
As machine learning (ML) models and datasets increase in complexity, the demand for methods that enhance explainability and interpretability becomes paramount. Prototypes, by encapsulating essential characteristics within data, offer…
Image recognition with prototypes is considered an interpretable alternative for black box deep learning models. Classification depends on the extent to which a test image "looks like" a prototype. However, perceptual similarity for humans…
By composing graphical models with deep learning architectures, we learn generative models with the strengths of both frameworks. The structured variational autoencoder (SVAE) inherits structure and interpretability from graphical models,…
Although substantial efforts have been made to learn disentangled representations under the variational autoencoder (VAE) framework, the fundamental properties to the dynamics of learning of most VAE models still remain unknown and…
Artificial intelligence-driven adaptive learning systems are reshaping education through data-driven adaptation of learning experiences. Yet many of these systems lack transparency, offering limited insight into how decisions are made. Most…
Multiple modalities often co-occur when describing natural phenomena. Learning a joint representation of these modalities should yield deeper and more useful representations. Previous generative approaches to multi-modal input either do not…