arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2012.04863cs.LGcs.AIcs.CV
收藏

Skillearn:受人类学习技能启发的机器学习

Skillearn: Machine Learning Inspired by Humans' Learning Skills

University of California San Diego(加利福尼亚大学圣迭戈分校)

Pengtao Xie, Xuefeng Du, Hao Ban

摘要:

人类作为这个星球上最强大的学习者,已经积累了很多学习技能,比如通过测试学习,交叉学习,自我解释,主动回忆等等。这些学习技能和方法使人类能够更有效地学习新的主题。我们有兴趣研究人类的学习技能是否可以用来帮助机器更好地学习。具体来说,我们的目标是将这些技能形式化,并利用它们来训练更好的机器学习(ML)模型。为了实现这一目标,我们开发了一个通用框架Skillearn,它提供了一种原则性的方法来数学地表示人类的学习技能,并使用形式化表示的技能来改进ML模型的训练。在两个案例研究中,我们应用Skillearn来形式化人类的两种学习技能:通过测试学习和交错学习,并使用形式化的技能来改进神经结构搜索。在各种数据集上的实验表明,使用Skillearn形式化的技能进行训练,ML模型的性能显着提高。

英文摘要:

Humans, as the most powerful learners on the planet, have accumulated a lot of learning skills, such as learning through tests, interleaving learning, self-explanation, active recalling, to name a few. These learning skills and methodologies enable humans to learn new topics more effectively and efficiently. We are interested in investigating whether humans' learning skills can be borrowed to help machines to learn better. Specifically, we aim to formalize these skills and leverage them to train better machine learning (ML) models. To achieve this goal, we develop a general framework -- Skillearn, which provides a principled way to represent humans' learning skills mathematically and use the formally-represented skills to improve the training of ML models. In two case studies, we apply Skillearn to formalize two learning skills of humans: learning by passing tests and interleaving learning, and use the formalized skills to improve neural architecture search. Experiments on various datasets show that trained using the skills formalized by Skillearn, ML models achieve significantly better performance.

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。

↑