arXiv research

Paper proposes a human-algorithm approach to reduce medical device recall risk and workload.

Interpreting neural network decisions and the information learned in intermediate layers is still a challenge due to the opaque internal state and shared non-linear interactions. Although (Kim et al, 2017) proposed to interpret intermediate layers by quantifying its ability to distinguish a user-defined concept (from r…

We study the effectiveness of several techniques to personalize end-to-end speech models and improve the recognition of proper names relevant to the user. These techniques differ in the amounts of user effort required to provide supervision, and are evaluated on how they impact speech recognition performance. We propos…

Study improves detection of cryptocurrency pump-and-dump schemes.

RAGuard improves safety in LLMs for offshore wind maintenance.

Recall assistance methods are among the key aspects that improve the accuracy of online dietary assessment surveys. These methods still mainly rely on experience of trained interviewers with nutritional background, but data driven approaches could improve cost-efficiency and scalability of automated dietary assessment.…

New algorithm reduces online learning regret for bounded recall games.

This paper introduces a new method to train normalizing flows using precision-recall divergences.

Improved DDPMs achieve high log-likelihoods and sample quality with fewer passes.

The study examines how class imbalance affects precision-recall curves.

New metrics improve reliability of image generation evaluation.

Smooth calibration improves forecast reliability even with leaked information.

This study is motivated by the magnitude of the problem of Louisiana high school dropout and its negative impacts on individual and public well-being. Our goal is to predict students who are at risk of high school dropout, by examining Louisiana administrative dataset. Due to the imbalanced nature of the dataset, imbal…

The study formalizes temporal precision and recall for anomaly detection in sequences.

KATA improves associative recall by optimizing feature maps derived from nonnegative attention weights.

For information retrieval and binary classification, we show that precision at the top (or precision at k) and recall at the top (or recall at k) are maximised by thresholding the posterior probability of the positive class. This finding is a consequence of a result on constrained minimisation of the cost-sensitive exp…

Unified and extended precision-recall metrics for generative models.

Transformers can store facts efficiently using associative memories.

LDP speeds up causal discovery by partitioning, improving VAS recall and runtime.

We recall the similarities between the concepts and techniques of Thermodynamics and Roegenian Economics. The Phase Diagram for a Roegenian economic system highlights a triple point and a critical point, with related explanations. These ideas can be used to improve our knowledge and understanding of the nature of devel…

Recalls intrinsically harmonic forms and open problems.

LLMs can memorize economic data and recall exact values before their training cutoff.

Paper tackles imbalanced binary classification by optimizing precision and recall directly.

The paper proposes a method to improve random forest classification accuracy by weighting trees based on their decision path reliability.

Over the last decade there has been increasing concern about the biases embodied in traditional evaluation methods for Natural Language Processing/Learning, particularly methods borrowed from Information Retrieval. Without knowledge of the Bias and Prevalence of the contingency being tested, or equivalently the expecta…

Classifiers trained on data sets possessing an imbalanced class distribution are known to exhibit poor generalisation performance. This is known as the imbalanced learning problem. The problem becomes particularly acute when we consider incremental classifiers operating on imbalanced data streams, especially when the l…

In this article we revisit the definition of Precision-Recall (PR) curves for generative models proposed by Sajjadi et al. (arXiv:1806.00035). Rather than providing a scalar for generative quality, PR curves distinguish mode-collapse (poor recall) and bad quality (poor precision). We first generalize their formulation …

New method improves causal discovery in time series with latent confounders.

Framework for precise recall control in spatial conflation tasks.

A new method for generating replay samples on the fly, optimizing for not forgetting.

Proposes a new tree-based algorithm for class-imbalanced data.

New model detects crying in real-world settings with improved accuracy.

A number of classification problems need to deal with data imbalance between classes. Often it is desired to have a high recall on the minority class while maintaining a high precision on the majority class. In this paper, we review a number of resampling techniques proposed in literature to handle unbalanced datasets …

The paper critiques and expands on common evaluation metrics in machine learning.

The increase in data collection has made data annotation an interesting and valuable task in the contemporary world. This paper presents a new methodology for quickly annotating data using click-supervision and hierarchical object detection. The proposed work is semi-automatic in nature where the task of annotations is…

Study develops and improves risk models using machine learning methods.

We recall and partially improve four versions of smooth, non-abelian gerbes: Cech cocycles, classifying maps, bundle gerbes, and principal 2-bundles. We prove that all these four versions are equivalent, and so establish new relations between interesting recent developments. Prominent partial results we prove are a bij…

Model infers mineral locations from geospatial data, improving predictions with auxiliary data.

New findings show tool-augmented models can recall unlimited facts, outperforming purely memorized models.

In many environments only a tiny subset of all states yield high reward. In these cases, few of the interactions with the environment provide a relevant learning signal. Hence, we may want to preferentially train on those high-reward states and the probable trajectories leading to them. To this end, we advocate for the…

Survey on heat equation estimates on manifolds.

Machine Learning (ML) helps us to recognize patterns from raw data. ML is used in numerous domains i.e. biomedical, agricultural, food technology, etc. Despite recent technological advancements, there is still room for substantial improvement in prediction. Current ML models are based on classical theories of probabili…

AI random forest model improves credit risk scoring for Azerbaijani SMEs.

The optimal ranking score between precision and recall is rarely F1 and can be found using specific methods.

Recalls and refines the concept of algebraically rectifiable curves.

Efficiently selects nearest neighbors for labeling to speed up active learning.

DIAL learns embeddings to maximize recall and accuracy for entity resolution.

Transformers recall from long distributions with statistical guarantees.