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 1409.3358cs.SEcs.LGcs.NE
收藏

为深度学习构建程序向量表示

Building Program Vector Representations for Deep Learning

Peking University(北京大学)

Lili Mou, Ge Li, Yuxuan Liu, Hao Peng, Zhi Jin, Yan Xu, Lu Zhang

摘要:

深度学习在人工智能的各个领域都取得了重大突破。深度学习的优势包括能够捕获高度复杂的特征,人类工程学的参与程度较低等。然而,由于纯反向传播无法有效地训练深度架构,因此实际上仍然不可能使用深度学习来分析程序。在这篇开创性的论文中,我们提出了构建程序向量表示的“编码标准”,这是用于程序分析的深度学习的前提。我们的表示学习方法直接使深度学习在这个新领域成为现实。我们从定性和定量两个方面评估学习的向量表示。我们的结论是,基于实验,编码标准是成功的,在建立程序表示。为了评估深度学习是否有利于程序分析,我们将表示输入深度神经网络,并在程序分类任务中实现比“浅层”方法更高的准确性,例如逻辑回归和支持向量机。这一结果证实了深度学习分析程序的可行性。它也提供了它在这一新领域取得成功的主要证据。我们相信,在不久的将来,深度学习将成为程序分析的杰出技术。

英文摘要:

Deep learning has made significant breakthroughs in various fields of artificial intelligence. Advantages of deep learning include the ability to capture highly complicated features, weak involvement of human engineering, etc. However, it is still virtually impossible to use deep learning to analyze programs since deep architectures cannot be trained effectively with pure back propagation. In this pioneering paper, we propose the "coding criterion" to build program vector representations, which are the premise of deep learning for program analysis. Our representation learning approach directly makes deep learning a reality in this new field. We evaluate the learned vector representations both qualitatively and quantitatively. We conclude, based on the experiments, the coding criterion is successful in building program representations. To evaluate whether deep learning is beneficial for program analysis, we feed the representations to deep neural networks, and achieve higher accuracy in the program classification task than "shallow" methods, such as logistic regression and the support vector machine. This result confirms the feasibility of deep learning to analyze programs. It also gives primary evidence of its success in this new field. We believe deep learning will become an outstanding technique for program analysis in the near future.

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。

↑