arXiv subjects

Xufan Zhang

Publications and source records attributed to Xufan Zhang.

3 recordsLinked to original sources

arXiv2019

Software Engineering Practice in the Development of Deep Learning Applications

Deep-Learning(DL) applications have been widely employed to assist in various tasks. They are constructed based on a data-driven programming paradigm that is different from conventional software applications. Given the increasing popularity and importance of DL applications, software engineering practitioners have some techniques specifically for them. However, little research is conducted to identify the challenges and lacks in practice. To fill this gap, in this paper, we surveyed 195 practitioners to understand their insight and experience in the software engineering practice of DL applications. Specifically, we asked the respondents to identify lacks and challenges in the practice of the development life cycle of DL applications. The results present 13 findings that provide us with a better understanding of software engineering practice of DL applications. Further, we distil these findings into 7 actionable recommendations for software engineering researchers and practitioners to improve the development of DL applications.

cs.SE↗

arXiv2019

NeuralVis: Visualizing and Interpreting Deep Learning Models

Deep Neural Network(DNN) techniques have been prevalent in software engineering. They are employed to faciliatate various software engineering tasks and embedded into many software applications. However, analyzing and understanding their behaviors is a difficult task for software engineers. In this paper, to support software engineers in visualizing and interpreting deep learning models, we present NeuralVis, an instance-based visualization tool for DNN. NeuralVis is designed for: 1). visualizing the structure of DNN models, i.e., components, layers, as well as connections; 2). visualizing the data transformation process; 3). integrating existing adversarial attack algorithms for test input generation; 4). comparing intermediate outputs of different instances to guide the test input generation; To demonstrate the effectiveness of NeuralVis, we conduct an user study involving ten participants on two classic DNN models, i.e., LeNet and VGG-12. The result shows NeuralVis can assist developers in identifying the critical features that determines the prediction results. Video: https://youtu.be/hRxCovrOZFI

cs.SE↗

arXiv2019

The domino shuffling height process and its hydrodynamic limit

The famous domino shuffling algorithm was invented to generate the domino tilings of the Aztec Diamond. Using the domino height function, we view the domino shuffling procedure as a discrete-time random height process on the plane. The hydrodynamic limit from an arbitrary continuous profile is deduced to be the unique viscosity solution of a Hamilton-Jacobi equation $u_t+H(u_x)=0$, where the determinant of the Hessian of $H$ is negative everywhere. The proof involves interpolation of the discrete process and analysis of the limiting semigroup of the evolution. In order to identify the limit, we use the theories of dimer models as well as Hamilton-Jacobi equations. It seems that our result is the first example in $d>1$ where such a full hydrodynamic limit with a nonconvex Hamiltonian can be obtained for a discrete system. We also define the shuffling height process for more general periodic dimer models, where we expect similar results to hold.

math.PR↗