Scalable Recollections for Continual Lifelong Learning

Matthew D Riemer
Matthew D Riemer
Djallel Bouneffouf
Djallel Bouneffouf

national conference on artificial intelligence, 2017.

Cited by: 8|Views12
Weibo:
We have proposed and experimentally validated a general purpose Scalable Recollection Module that is designed to scale for very long time-frames

Abstract:

Given the recent success of Deep Learning applied to a variety of single tasks, it is natural to consider more human-realistic settings. Perhaps the most difficult of these settings is that of continual lifelong learning, where the model must learn online over a continuous stream of non-stationary data. A successful continual lifelong lea...More

Code:

Data:

0
Full Text
Bibtex
Weibo
Your rating :
0

 

Tags
Comments