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 1801.04342cs.LGcs.AIstat.ML
收藏

神经程序中符号表达式与黑箱函数求值的结合

Combining Symbolic Expressions and Black-box Function Evaluations in Neural Programs

University of California(加利福尼亚大学);California Institute of Technology(加州理工学院)

Forough Arabshahi, Sameer Singh, Animashree Anandkumar

摘要:

神经编程涉及训练神经网络从数据中学习程序、数学或逻辑。以往的工作未能取得良好的泛化性能,特别是在问题和程序的高复杂性或大型域。这是因为它们主要依赖于不捕获程序结构的黑盒函数评估,或者依赖于获得昂贵的详细执行跟踪,因此训练数据对所考虑的域的覆盖率很差。我们提出了一个新的框架,利用黑盒功能评估,结合符号表达式,定义给定的功能之间的关系。我们采用树LSTM将符号表达式树的结构。我们对函数求值数据中的数字使用树编码,基于它们的十进制表示。我们提出了一个评估基准,这个任务,以证明我们提出的模型结合了符号推理和功能评估在一个富有成效的方式,在我们的实验中获得高精度。我们的框架更好地推广到更高深度的表达式,并能够用有效的补全来填充偏方程。

英文摘要:

Neural programming involves training neural networks to learn programs, mathematics, or logic from data. Previous works have failed to achieve good generalization performance, especially on problems and programs with high complexity or on large domains. This is because they mostly rely either on black-box function evaluations that do not capture the structure of the program, or on detailed execution traces that are expensive to obtain, and hence the training data has poor coverage of the domain under consideration. We present a novel framework that utilizes black-box function evaluations, in conjunction with symbolic expressions that define relationships between the given functions. We employ tree LSTMs to incorporate the structure of the symbolic expression trees. We use tree encoding for numbers present in function evaluation data, based on their decimal representation. We present an evaluation benchmark for this task to demonstrate our proposed model combines symbolic reasoning and function evaluation in a fruitful manner, obtaining high accuracies in our experiments. Our framework generalizes significantly better to expressions of higher depth and is able to fill partial equations with valid completions.

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。

↑