Výsledky vyhledávání

Report

Hierarchical Conditional Tabular GAN for Multi-Tabular Synthetic Data Generation

Autor: Ågren, Wilhelm, Sosa, Victorio Úbeda

The generation of synthetic data is a state-of-the-art approach to leverage when access to real data is limited or privacy regulations limit the usability of sensitive data. A fair amount of research has been conducted on synthetic data generation fo

Externí odkaz: http://arxiv.org/abs/2411.07009

Zobrazit plný text záznamu

Report

Repr Types: One Abstraction to Rule Them All

Autor: Palmkvist, Viktor, Thuné, Anders Ågren, Castegren, Elias, Broman, David

The choice of how to represent an abstract type can have a major impact on the performance of a program, yet mainstream compilers cannot perform optimizations at such a high level. When dealing with optimizations of data type representations, an impo

Externí odkaz: http://arxiv.org/abs/2409.07950

Zobrazit plný text záznamu

Report

The NT-Xent loss upper bound

Autor: Ågren, Wilhelm

Self-supervised learning is a growing paradigm in deep representation learning, showing great generalization capabilities and competitive performance in low-labeled data regimes. The SimCLR framework proposes the NT-Xent loss for contrastive represen

Externí odkaz: http://arxiv.org/abs/2205.03169

Zobrazit plný text záznamu

Report

Agile Beyond Teams and Feedback Beyond Software in Automotive Systems

Autor: Ågren, S. Magnus, Heldal, Rogardt, Knauss, Eric, Pelliccione, Patrizio

In order to increase the ability to build complex, software-intensive systems, as well as to decrease time-to-market for new functionality, automotive companies aim to scale agile methods beyond individual teams. This is challenging, given the specif

Externí odkaz: http://arxiv.org/abs/2203.13130

Zobrazit plný text záznamu