相关论文: Informative Perturbation Selection for Uncertainty…

We pose uncertainty quantification and exploration in online decision-making as a problem of training and generation from an autoregressive sequence model, an area experiencing rapid innovation. Our approach rests on viewing uncertainty as…

A major challenge in Explainable AI is in correctly interpreting activations of hidden neurons: accurate interpretations would help answer the question of what a deep learning system internally detects as relevant in the input, demystifying…

Bayesian decision theory provides an elegant framework for acting optimally under uncertainty when tractable posterior distributions are available. Modern Bayesian models, however, typically involve intractable posteriors that are…

Engineering and applied science rely on computational experiments to rigorously study physical systems. The mathematical models used to probe these systems are highly complex, and sampling-intensive studies often require prohibitively many…

Sequential generative models conditioned on uncertain rewards are central to AI-driven scientific discovery, yet the epistemic uncertainty they inherit from imperfect reward estimates remains unquantified. We propagate this uncertainty…

This work presents a step towards utilizing incrementally-improving symbolic perception knowledge of the robot's surroundings for provably correct reactive control synthesis applied to an autonomous driving problem. Combining abstract…

Selective classifiers improve model reliability by abstaining on inputs the model deems uncertain. However, few practical approaches achieve the gold-standard performance of a perfect-ordering oracle that accepts examples exactly in order…

Recent models for natural language understanding are inclined to exploit simple patterns in datasets, commonly known as shortcuts. These shortcuts hinge on spurious correlations between labels and latent features existing in the training…

The need for transparency of predictive systems based on Machine Learning algorithms arises as a consequence of their ever-increasing proliferation in the industry. Whenever black-box algorithmic predictions influence human affairs, the…

Prior work on probing neural networks primarily relies on input-space analysis or parameter perturbation, both of which face fundamental limitations in accessing structural information encoded in intermediate representations. We introduce…

As black-box machine learning models grow in complexity and find applications in high-stakes scenarios, it is imperative to provide explanations for their predictions. Although Local Interpretable Model-agnostic Explanations (LIME) [22] is…

In this article, we present a leap-forward expansion to the study of explainability in neural networks by considering explanations as answers to abstract reasoning-based questions. With $P$ as the prediction from a neural network, these…

Explainability is a gateway between Artificial Intelligence and society as the current popular deep learning models are generally weak in explaining the reasoning process and prediction results. Local Interpretable Model-agnostic…

The explainability of machine learning algorithms is crucial, and numerous methods have emerged recently. Local, post-hoc methods assign an attribution score to each feature, indicating its importance for the prediction. However, these…

Local explanation methods such as LIME have become popular in MIR as tools for generating post-hoc, model-agnostic explanations of a model's classification decisions. The basic idea is to identify a small set of human-understandable…

The deployment of pre-trained perception models in novel environments often leads to performance degradation due to distributional shifts. Although recent artificial intelligence approaches for metacognition use logical rules to…

Experimental user studies evaluating the effectiveness of different subtypes of post-hoc explanations for black-box models are largely nonexistent. Therefore, the aim of this study was to investigate and evaluate how different types of…

Chaotic systems pose fundamental challenges for data-driven dynamics discovery, as small modeling errors lead to exponentially growing trajectory discrepancies. Since exact long-term prediction is unattainable, it is natural to ask what a…

This technical note considers the sampling of outcomes that provide the greatest amount of information about the structure of underlying world models. This generalisation furnishes a principled approach to structure learning under a…

Local Interpretable Model-Agnostic Explanations (LIME) is a popular method to perform interpretability of any kind of Machine Learning (ML) model. It explains one ML prediction at a time, by learning a simple linear model around the…