相关论文: A categorical error sensitivity index (ISEC): A pr…

Mechanistic interpretability has identified functional subgraphs within large language models (LLMs), known as Transformer Circuits (TCs), that appear to implement specific algorithms. Yet we lack a formal, single-pass way to quantify when…

The paper introduces a novel framework based on category theory to enhance the explainability of artificial intelligence systems, particularly focusing on word embeddings. Key topics include the construction of categories $\mathcal{L}_T$…

Monte Carlo simulations are the primary methodology for evaluating Item Response Theory (IRT) methods, yet marginal reliability - the fundamental metric of data informativeness - is rarely treated as an explicit design factor. Unlike in…

Semantic segmentation is a computer vision task that associates a label with each pixel in an image. Modern approaches tend to introduce class embeddings into semantic segmentation for deeply utilizing category semantics, and regard…

Simulation can evaluate a statistical method for properties such as Type I Error, FDR, or bias on a grid of hypothesized parameter values. But what about the gaps between the grid-points? Continuous Simulation Extension (CSE) is a…

An examination of object recognition challenge leaderboards (ILSVRC, PASCAL-VOC) reveals that the top-performing classifiers typically exhibit small differences amongst themselves in terms of error rate/mAP. To better differentiate the top…

Probabilistic classifiers output confidence scores along with their predictions, and these confidence scores should be calibrated, i.e., they should reflect the reliability of the prediction. Confidence scores that minimize standard metrics…

Accurate semantic segmentation models typically require significant computational resources, inhibiting their use in practical applications. Recent works rely on well-crafted lightweight models to achieve fast inference. However, these…

Information criteria (IC) have been widely used in factor models to estimate an unknown number of latent factors. It has recently been shown that IC perform well in Common Correlated Effects (CCE) and related setups in selecting a set of…

Fairness in machine learning is predominantly evaluated through outcome-oriented metrics, such as Demographic parity, which measure whether predictions are statistically consistent across protected groups. However, these metrics cannot…

Over the past years, computer vision community has contributed to enormous progress in semantic image segmentation, a per-pixel classification task, crucial for dense scene understanding and rapidly becoming vital in lots of real-world…

Modern computational models in supervised machine learning are often highly parameterized universal approximators. As such, the value of the parameters is unimportant, and only the out of sample performance is considered. On the other hand…

Automation in Security Operations Centers (SOCs) plays a prominent role in alert classification and incident escalation. However, automated methods must be robust in the presence of imbalanced input data, which can negatively affect…

Complexity measures in the context of the Integrated Information Theory of consciousness try to quantify the strength of the causal connections between different neurons. This is done by minimizing the KL-divergence between a full system…

Time Series Anomaly Detection metrics serve as crucial tools for model evaluation. However, existing metrics suffer from several limitations: insufficient discriminative power, strong hyperparameter dependency, sensitivity to perturbations,…

Support estimation (SE) of a sparse signal refers to finding the location indices of the non-zero elements in a sparse representation. Most of the traditional approaches dealing with SE problem are iterative algorithms based on greedy…

Intermediate-Severity (IS) faults present milder symptoms compared to severe faults, and are more difficult to detect and diagnose due to their close resemblance to normal operating conditions. The lack of IS fault examples in the training…

Realizing edge intelligence consists of sensing, communication, training, and inference stages. Conventionally, the sensing and communication stages are executed sequentially, which results in excessive amount of dataset generation and…

Iterative feature space optimization involves systematically evaluating and adjusting the feature space to improve downstream task performance. However, existing works suffer from three key limitations:1) overlooking differences among data…

Semantic Embeddings are a popular way to represent knowledge in the field of zero-shot learning. We observe their interpretability and discuss their potential utility in a safety-critical context. Concretely, we propose to use them to add…