Editable Neural Networks

Editable Neural Networks
复制标题

可编辑的神经网络

DOI:
--
复制
发表时间:
2020
期刊:
International Conference on Learning Representations
影响因子:
--
通讯作者:
Artem Babenko
Artem Babenko
中科院分区:
--
文献类型:
--
作者:
A. Sinitsin;Vsevolod Plokhotnyuk;Dmitriy V. Pyrkin;Sergei Popov;Artem Babenko

文献摘要

参考文献

被引文献

相似文献

如今,深度神经网络被广泛用于各种任务,从图像分类和机器翻译到人脸识别和自动驾驶汽车。在许多应用中,一个单一的模型错误可能导致毁灭性的财务,声誉甚至危及生命的后果。因此,在模型出现错误时迅速纠正它们是至关重要的。在这项工作中,我们研究了神经网络编辑的问题-如何有效地修补特定样本上的模型错误,而不影响其他样本上的模型行为。也就是说,我们提出了可编辑训练,这是一种与模型无关的训练技术,鼓励快速编辑训练模型。我们实证证明了这种方法在大规模图像分类和机器翻译任务上的有效性。
These days deep neural networks are ubiquitously used in a wide range of tasks, from image classification and machine translation to face identification and self-driving cars. In many applications, a single model error can lead to devastating financial, reputational and even life-threatening consequences. Therefore, it is crucially important to correct model mistakes quickly as they appear. In this work, we investigate the problem of neural network editing - how one can efficiently patch a mistake of the model on a particular sample, without influencing the model behavior on other samples. Namely, we propose Editable Training, a model-agnostic training technique that encourages fast editing of the trained model. We empirically demonstrate the effectiveness of this method on large-scale image classification and machine translation tasks.
DOI: 10.18653/v1/d19-1221
发表时间: 2019-08
期刊: --
影响因子: --
作者:
Eric Wallace;Shi Feng;Nikhil Kandpal;Matt Gardner;Sameer Singh
通讯作者: Eric Wallace;Shi Feng;Nikhil Kandpal;Matt Gardner;Sameer Singh
深度(呃)学习。
DOI: 10.1523/jneurosci.0153-18.2018
发表时间: 2018
期刊: The Journal of neuroscience : the official journal of the Society for Neuroscience
影响因子: --
作者:
Srinivasan,Shyam;Greenspan,RalphJ;Stevens,CharlesF;Grover,Dhruv
通讯作者: Grover,Dhruv
DOI: 10.1109/tnnls.2018.2886017
发表时间: 2019-09-01
影响因子: 10.4
作者:
Yu, Xiaoyong;He, Pan;Li, Xiaolin
通讯作者: Li, Xiaolin
DOI: 10.1037/0033-295x.97.2.285
发表时间: 1990-04-01
影响因子: 5.4
作者:
RATCLIFF, R
通讯作者: RATCLIFF, R