arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2304.09499cs.LGcs.DM
收藏

具有无序目标的神经网络中的责任问题

The Responsibility Problem in Neural Networks with Unordered Targets

Queen Mary University of London(伦敦玛丽女王大学)

Ben Hayes, Charalampos Saitis, György Fazekas

AI总结:

针对无序目标与固定排列神经网络输出之间的责任问题,本文证明相关不连续性并非仅有一个,而是不可数无穷多个,凸显了研究无序数据神经网络的必要性。

摘要:

我们讨论了将无序对象映射到固定排列的神经网络输出时出现的不连续性,这被称为责任问题。先前工作通过识别单个不连续性证明了该问题的存在。在此,我们证明此类模型下的不连续性具有不可数无穷多个,从而推动对面向无序数据的神经网络的进一步研究。

英文摘要:

We discuss the discontinuities that arise when mapping unordered objects to neural network outputs of fixed permutation, referred to as the responsibility problem. Prior work has proved the existence of the issue by identifying a single discontinuity. Here, we show that discontinuities under such models are uncountably infinite, motivating further research into neural networks for unordered data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑