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:
影响因子:
--
通讯作者:
Artem Babenko
中科院分区:
文献类型:
--
作者:
A. Sinitsin;Vsevolod Plokhotnyuk;Dmitriy V. Pyrkin;Sergei Popov;Artem Babenko
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.
登录
查看更多内容
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
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
影响因子:
5.4
作者:
RATCLIFF, R
通讯作者:
RATCLIFF, R