Editable Neural Networks

04/01/2020
by   Anton Sinitsin, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/19/2020

Computer Assisted Translation with Neural Quality Estimation and Automatic Post-Editing

With the advent of neural machine translation, there has been a marked s...
research
06/23/2016

CUNI System for WMT16 Automatic Post-Editing and Multimodal Translation Tasks

Neural sequence to sequence learning recently became a very promising pa...
research
12/13/2022

Towards a general purpose machine translation system for Sranantongo

Machine translation for Sranantongo (Sranan, srn), a low-resource Creole...
research
06/04/2019

Post-editing Productivity with Neural Machine Translation: An Empirical Assessment of Speed and Quality in the Banking and Finance Domain

Neural machine translation (NMT) has set new quality standards in automa...
research
11/23/2022

Rank-One Editing of Encoder-Decoder Models

Large sequence to sequence models for tasks such as Neural Machine Trans...
research
02/28/2018

Memory-based Parameter Adaptation

Deep neural networks have excelled on a wide range of problems, from vis...
research
05/06/2020

Evaluation, Tuning and Interpretation of Neural Networks for Meteorological Applications

Neural networks have opened up many new opportunities to utilize remotel...

Please sign up or login with your details

Forgot password? Click here to reset