We present Azimuth, an open-source and easy-to-use tool to perform error analysis for text classification. Compared to other stages of the ML development cycle, such as model training and hyper-parameter tuning, the process and tooling for the error...
There are many hurdles that prevent the replication of existing work which hinders the development of new activity classification models. These hurdles include switching between multiple deep learning libraries and the development of boilerplate expe...
In this paper, we present our first proposal of a machine learning system for the classification of freshwater snails of the genus Radomaniola. We elaborate on the specific challenges encountered during system design, and how we tackled them; namely...
Compared to English, the amount of labeled data for Indonesian text classification tasks is very small. Recently developed multilingual language models have shown its ability to create multilingual representations effectively. This paper investigates...
We propose a new approach to promote safety in classification tasks with established concepts. Our approach -- called a conceptual safeguard -- acts as a verification layer for models that predict a target outcome by first predicting the presence of...
In this work, we investigate the efficacy of various adapter architectures on supervised binary classification tasks from the SuperGLUE benchmark as well as a supervised multi-class news category classification task from Kaggle. Specifically, we comp...
A classification theorem is obtained for a class of unital simple separable amenable Z-stable C*-algebras which exhausts all possible values of the Elliott invariant for unital stably finite simple separable amenable Z-stable C*-algebras. Moreover, i...
Dec 31, 2025 · In this article, we’ll take a deep dive into demonology and teach you about different types of demons based on mythology, classification, and rank with help from urban legends expert Sydney …
Ultra-high Spatial Resolution (UHSR) Land Cover Classification is increasingly important for urban analysis, enabling fine-scale planning, ecological monitoring, and infrastructure management. It identifies land cover types on sub-meter remote sensin...
The minimization of specific cases in binary classification, such as false negatives or false positives, grows increasingly important as humans begin to implement more machine learning into current products. While there are a few methods to put a bia...
For classification problems, trained deep neural networks return probabilities of class memberships. In this work we study convergence of the learned probabilities to the true conditional class probabilities. More specifically we consider sparse deep...
Feature engineering is one of the most costly aspects of developing effective machine learning models, and that cost is even greater in specialized problem domains, like malware classification, where expert skills are necessary to identify useful fea...
Text classification with hierarchical taxonomies is a fundamental requirement in IT Service Management (ITSM) systems, where support tickets must be categorized into tree-structured taxonomies. We present a dual-embedding centroid-based classificatio...
The variable stars in the VSX catalog are derived from a multitude of inhomogeneous data sources and classification tools. This inhomogeneity complicates our understanding of variable star types, statistics, and properties, and it directly affects at...
The top-k classification accuracy is one of the core metrics in machine learning. Here, k is conventionally a positive integer, such as 1 or 5, leading to top-1 or top-5 training objectives. In this work, we relax this assumption and optimize the mod...
article gives an overview of the aquatic communities in the British National Vegetation Classification system. The aquatic communities of the NVC were
Recently deep neural networks demonstrate competitive performances in classification and regression tasks for many temporal or sequential data. However, it is still hard to understand the classification mechanisms of temporal deep neural networks. In...
Shesop is an integrated system to make human lives more easily and to help people in terms of healthcare. Stress and influenza classification is a part of Shesop's application for a healthcare devices such as smartwatch, polar and fitbit. The main ob...
This report presents a comprehensive study on deep learning models for brand logo classification in real-world scenarios. The dataset contains 3,717 labeled images of logos from ten prominent brands. Two types of models, Convolutional Neural Networks...
Robots need to perceive persons in their surroundings for safety and to interact with them. In this paper, we present a person segmentation and action classification approach that operates on 3D scans of hemisphere field of view LiDAR sensors. We rec...