The Parallel Transfer of Task Knowledge Using Dynamic Learning Rates Based on a Measure of Relatedness
作者:
DANIEL L SILVER,
期刊:
Connection Science
(Taylor Available online 1996)
卷期:
Volume 8,
issue 2
页码: 277-294
ISSN:0954-0091
年代: 1996
DOI:10.1080/095400996116929
出版商: Taylor & Francis Group
关键词: Artificial Neural Networks;Learning To Learn;Knowledge-based Inductive Bias;Task Relatedness;Task Knowledge Transfer;Parallel Learning
数据来源: Taylor
摘要:
With a distinction made between two forms of task knowledge transfer, 'representational' and 'functional', eta MTL, a modified version of the multiple task learning (MTL) method of functional (parallel) transfer, is introduced. The eta MTL method employs a separate learning rate, etak, for each task output node k. etak varies as a function of a measure of relatedness, Rk, between the kth task and the primary task of interest. Results of experiments demonstrate the ability of eta MTL to dynamically select the most related source task(s) for the functional transfer of prior domain knowledge. The eta MTL method of learning is nearly equivalent to standard MTL when all parallel tasks are sufficiently related to the primary task, and is similar to single task learning when none of the parallel tasks are related to the primary task.
点击下载:
PDF (398KB)
返 回