Sequential Consolidation of Learned Task Knowledge
Sequential Consolidation of Learned Task Knowledge
复制标题
所学任务知识的顺序巩固
DOI：
10.1007/978-3-540-24840-8_16
复制
发表时间：
2004
期刊：
影响因子：
--
通讯作者：
R. Poirier
中科院分区：
文献类型：
--
作者：
D. Silver;R. Poirier
终身机器学习的一个基本问题是如何在长期记忆结构（领域知识）中巩固学习任务的知识，而不会丢失先验知识。巩固的领域知识可以更有效地利用记忆，并且可以在学习未来任务时用于更高效和有效的知识转移。回顾了基于知识的归纳学习和使用多任务学习（MTL）神经网络转移任务知识的相关背景材料。提出了一种任务知识巩固理论，该理论采用大MTL网络作为长时记忆结构，通过任务复述克服了稳定性-可塑性问题和先验知识的丢失。该理论进行了测试的合成域不同的任务，它表明，在适当的条件下，任务知识可以顺序巩固在MTL网络没有损失的先验知识。事实上，可以观察到巩固的领域知识的准确性稳步增加。
A fundamental problem of life-long machine learning is how to consolidate the knowledge of a learned task within a long-term memory structure (domain knowledge) without the loss of prior knowledge. Consolidated domain knowledge makes more efficient use of memory and can be used for more efficient and effective transfer of knowledge when learning future tasks. Relevant background material on knowledge based inductive learning and the transfer of task knowledge using multiple task learning (MTL) neural networks is reviewed. A theory of task knowledge consolidation is presented that uses a large MTL network as the long-term memory structure and task rehearsal to overcome the stability-plasticity problem and the loss of prior knowledge. The theory is tested on a synthetic domain of diverse tasks and it is shown that, under the proper conditions, task knowledge can be sequentially consolidated within an MTL network without loss of prior knowledge. In fact, a steady increase in the accuracy of consolidated domain knowledge is observed.