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 1903.12366cs.NEcs.LGcs.PL
收藏

使用结构化输入和模块化改进学习

Using Structured Input and Modularity for Improved Learning

IBM Research(IBM研究院)

Zehra Sura, Tong Chen, Hyojin Sung

摘要:

我们描述了一种利用输入数据的已知结构使学习更有效的方法。我们的工作是在程序设计语言领域,我们使用深度神经网络进行程序分析。计算机程序包含大量结构信息(如循环嵌套、条件块和数据范围),这些信息与程序分析有关。在这种情况下,神经网络必须学习识别结构,并学习问题的目标函数。然而,在这个领域的结构信息是很容易访问的软件与编译器工具和解析器的可用性定义良好的程序设计语言。我们利用已知输入数据结构的方法包括:(1)对输入数据进行预处理以暴露相关结构,以及(2)通过将输入数据的结构作为网络设计的组成部分来构建神经网络。该方法具有模块化神经网络的效果,这有助于分解复杂性,并导致整个网络的更有效的训练。我们将此方法应用于一个示例代码分析问题,并表明它可以实现更高的精度与较小的网络规模和更少的训练样本。此外,该方法是鲁棒的,对具有不同分布的输入数据同样表现良好。

英文摘要:

We describe a method for utilizing the known structure of input data to make learning more efficient. Our work is in the domain of programming languages, and we use deep neural networks to do program analysis. Computer programs include a lot of structural information (such as loop nests, conditional blocks, and data scopes), which is pertinent to program analysis. In this case, the neural network has to learn to recognize the structure, and also learn the target function for the problem. However, the structural information in this domain is readily accessible to software with the availability of compiler tools and parsers for well-defined programming languages. Our method for utilizing the known structure of input data includes: (1) pre-processing the input data to expose relevant structures, and (2) constructing neural networks by incorporating the structure of the input data as an integral part of the network design. The method has the effect of modularizing the neural network which helps break down complexity, and results in more efficient training of the overall network. We apply this method to an example code analysis problem, and show that it can achieve higher accuracy with a smaller network size and fewer training examples. Further, the method is robust, performing equally well on input data with different distributions.

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。

↑