SNR: Sub-Network Routing for Flexible Parameter Sharing in Multi-task Learning

THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, pp. 216-223, 2019.

Cited by: 18|Views113
EI

Abstract:

Machine learning applications, such as object detection and content recommendation, often require training a single model to predict multiple targets at the same time. Multi-task learning through neural networks became popular recently, because it not only helps improve the accuracy of many prediction tasks when they are related, but also...More

Code:

Data:

Your rating :
0

 

Tags
Comments