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 2005.04318cs.LGcs.AIstat.ML
收藏

转换任务表示以执行新任务

Transforming task representations to perform novel tasks

Stanford University(斯坦福大学)

Andrew K. Lampinen, James L. McClelland

摘要:

智力的一个重要方面是在没有任何直接经验(zero-shot)的情况下适应新任务的能力,这是基于它与先前任务的关系。人类可以表现出这种认知灵活性。相比之下,在特定任务中实现超人性能的模型往往无法适应哪怕是轻微的任务变化。为了解决这个问题,我们提出了一个通用的计算框架,以适应新的任务的基础上,他们的关系,以前的任务。我们从学习任务的向量表示开始。为了适应新的任务,我们提出了元映射,高阶任务,转换基本的任务表示。我们证明了这个框架在各种各样的任务和计算范式,从回归到图像分类和强化学习的有效性。我们比较了人类的适应性和基于语言的方法零样本学习。在这些领域中,元映射是成功的,通常在没有任何数据的情况下,在新任务上实现80-90%的性能,即使新任务与先前的经验直接矛盾。我们进一步表明,元映射不仅可以通过学习的关系推广到新的任务,而且还可以使用训练过程中看不到的新关系进行推广。最后,使用元映射作为起点可以大大加快后续对新任务的学习,并大大减少学习时间和累积错误。我们的研究结果提供了一个可能的智能适应性的计算基础的洞察力,并提供了一个可能的框架建模认知灵活性和构建更灵活的人工智能系统。

英文摘要:

An important aspect of intelligence is the ability to adapt to a novel task without any direct experience (zero-shot), based on its relationship to previous tasks. Humans can exhibit this cognitive flexibility. By contrast, models that achieve superhuman performance in specific tasks often fail to adapt to even slight task alterations. To address this, we propose a general computational framework for adapting to novel tasks based on their relationship to prior tasks. We begin by learning vector representations of tasks. To adapt to new tasks, we propose meta-mappings, higher-order tasks that transform basic task representations. We demonstrate the effectiveness of this framework across a wide variety of tasks and computational paradigms, ranging from regression to image classification and reinforcement learning. We compare to both human adaptability and language-based approaches to zero-shot learning. Across these domains, meta-mapping is successful, often achieving 80-90% performance, without any data, on a novel task, even when the new task directly contradicts prior experience. We further show that meta-mapping can not only generalize to new tasks via learned relationships, but can also generalize using novel relationships unseen during training. Finally, using meta-mapping as a starting point can dramatically accelerate later learning on a new task, and reduce learning time and cumulative error substantially. Our results provide insight into a possible computational basis of intelligent adaptability and offer a possible framework for modeling cognitive flexibility and building more flexible artificial intelligence systems.

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。

↑