arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.03744cs.LGcs.AIstat.ML
收藏

生成性持续概念学习

Generative Continual Concept Learning

University of Pennsylvania(宾夕法尼亚大学);HRL Laboratories, LLC(HRL实验室有限责任公司);Stanford University(斯坦福大学)

Mohammad Rostami, Soheil Kolouri, James McClelland, Praveen Pilly

摘要:

在学习了一个概念之后,人类还能够通过只观察少数标记的实例而不干扰过去学习的知识来不断地将他们学习的概念推广到新的领域。相比之下,在持续学习环境中有效地学习概念仍然是当前人工智能算法的公开挑战,因为持续的模型再训练是必要的。受并行分布式处理学习和互补学习系统理论的启发,我们开发了一个计算模型,该模型能够使用少量标记样本有效地将先前学习的概念扩展到新的领域。我们将概念的新形式与其过去学习的形式结合在一个嵌入空间中,以实现有效的持续学习。这样做,生成分布被学习,使得它在嵌入空间中的任务之间共享,并对抽象概念进行建模。这个过程使模型能够生成伪数据点来重放过去的经验,以解决灾难性遗忘。

英文摘要:

After learning a concept, humans are also able to continually generalize their learned concepts to new domains by observing only a few labeled instances without any interference with the past learned knowledge. In contrast, learning concepts efficiently in a continual learning setting remains an open challenge for current Artificial Intelligence algorithms as persistent model retraining is necessary. Inspired by the Parallel Distributed Processing learning and the Complementary Learning Systems theories, we develop a computational model that is able to expand its previously learned concepts efficiently to new domains using a few labeled samples. We couple the new form of a concept to its past learned forms in an embedding space for effective continual learning. Doing so, a generative distribution is learned such that it is shared across the tasks in the embedding space and models the abstract concepts. This procedure enables the model to generate pseudo-data points to replay the past experience to tackle catastrophic forgetting.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑