arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1907.13494cs.CVcs.NEstat.ML
收藏

关于学习和预测弹跳物体长期动力学的困难

On the difficulty of learning and predicting the long-term dynamics of bouncing objects

University of Padova(帕多瓦大学)

Alberto Cenzato, Alberto Testolin, Marco Zorzi

摘要:

准确预测周围环境的能力是生物和人工智能的基本原则。近年来,已经提出了各种方法来学习预测在视觉场景中交互的对象的物理动力学。在这里,我们对几种最先进的无监督深度学习模型进行了系统的实证评估,这些模型被认为能够学习由弹跳对象的合成视频组成的流行数据集的时空结构。我们发现,大多数模型确实获得了高精度的标准基准预测序列的下一帧,其中一个甚至达到了最先进的性能。然而,所有的模型都不符合更具挑战性的任务,生成多个连续的帧。我们的研究结果表明,执行短期预测的能力并不意味着该模型已经捕捉到了视觉环境的底层结构和动态,因此需要仔细重新思考通常用于评估时间模型的指标。我们还调查了学习成果是否会受到使用基于知识的教学。

英文摘要:

The ability to accurately predict the surrounding environment is a foundational principle of intelligence in biological and artificial agents. In recent years, a variety of approaches have been proposed for learning to predict the physical dynamics of objects interacting in a visual scene. Here we conduct a systematic empirical evaluation of several state-of-the-art unsupervised deep learning models that are considered capable of learning the spatio-temporal structure of a popular dataset composed by synthetic videos of bouncing objects. We show that most of the models indeed obtain high accuracy on the standard benchmark of predicting the next frame of a sequence, and one of them even achieves state-of-the-art performance. However, all models fall short when probed with the more challenging task of generating multiple successive frames. Our results show that the ability to perform short-term predictions does not imply that the model has captured the underlying structure and dynamics of the visual environment, thereby calling for a careful rethinking of the metrics commonly adopted for evaluating temporal models. We also investigate whether the learning outcome could be affected by the use of curriculum-based teaching.

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。

↑