scholarly journals Image-based many-language programming language identification

2021 ◽  
Vol 7 ◽  
pp. e631
Author(s):  
Francesca Del Bonifro ◽  
Maurizio Gabbrielli ◽  
Antonio Lategano ◽  
Stefano Zacchiroli
Keyword(s):  
Neural Networks ◽  
Programming Languages ◽  
Programming Language ◽  
Real World ◽  
Program Comprehension ◽  
Language Identification ◽  
Specific Character ◽  
Automatic Program ◽  
Video Tutorials ◽  
Code Understanding

Programming language identification (PLI) is a common need in automatic program comprehension as well as a prerequisite for deeper forms of code understanding. Image-based approaches to PLI have recently emerged and are appealing due to their applicability to code screenshots and programming video tutorials. However, they remain limited to the recognition of a small amount of programming languages (up to 10 languages in the literature). We show that it is possible to perform image-based PLI on a large number of programming languages (up to 149 in our experiments) with high (92%) precision and recall, using convolutional neural networks (CNNs) and transfer learning, starting from readily-available pretrained CNNs. Results were obtained on a large real-world dataset of 300,000 code snippets extracted from popular GitHub repositories. By scrambling specific character classes and comparing identification performances we also show that the characters that contribute the most to the visual recognizability of programming languages are symbols (e.g., punctuation, mathematical operators and parentheses), followed by alphabetic characters, with digits and indentation having a negligible impact.

PERANGKAT LUNAK KOMPUTER

2020 ◽  
Author(s):  
Cut Nabilah Damni
Keyword(s):  
Programming Languages ◽  
Programming Language ◽  
Operating Systems ◽  
Source Code ◽  
Computer Software ◽  
Computer Programs ◽  
Application Systems ◽  
Executable Programs

AbstrakSoftware komputer atau perangkat lunak komputer merupakan kumpulan instruksi (program atau prosedur) untuk dapat melaksanakan pekerjaan secara otomatis dengan cara mengolah atau memproses kumpulan intruksi (data) yang diberikan. (Yahfizham, 2019 : 19) Sebagian besar dari software komputer dibuat oleh (programmer) dengan menggunakan bahasa pemprograman. Orang yang membuat bahasa pemprograman menuliskan perintah dalam bahasa pemprograman seperti layaknya bahasa yang digunakan oleh orang pada umumnya dalam melakukan perbincangan. Perintah-perintah tersebut dinamakan (source code). Program komputer lainnya dinamakan (compiler) yang digunakan pada (source code) dan kemudian mengubah perintah tersebut kedalam bahasa yang dimengerti oleh komputer lalu hasilnya dinamakan program executable (EXE). Pada dasarnya, komputer selalu memiliki perangkat lunak komputer atau software yang terdiri dari sistem operasi, sistem aplikasi dan bahasa pemograman.AbstractComputer software or computer software is a collection of instructions (programs or procedures) to be able to carry out work automatically by processing or processing the collection of instructions (data) provided. (Yahfizham, 2019: 19) Most of the computer software is made by (programmers) using the programming language. People who make programming languages write commands in the programming language like the language used by people in general in conducting conversation. The commands are called (source code). Other computer programs called (compilers) are used in (source code) and then change the command into a language understood by the computer and the results are called executable programs (EXE). Basically, computers always have computer software or software consisting of operating systems, application systems and programming languages.

scholarly journals What do class comments tell us? An investigation of comment evolution and practices in Pharo Smalltalk

2021 ◽  
Vol 26 (6) ◽  
Author(s):  
Pooja Rani ◽  
Sebastiano Panichella ◽  
Manuel Leuenberger ◽  
Mohammad Ghafari ◽  
Oscar Nierstrasz
Keyword(s):  
Empirical Study ◽  
Programming Languages ◽  
Program Comprehension ◽  
Assessment Tools ◽  
Support Program ◽  
Writing Style ◽  
High Quality ◽  
Types Of Information ◽  
Similar Code

Abstract Context Previous studies have characterized code comments in various programming languages, showing how high quality of code comments is crucial to support program comprehension activities, and to improve the effectiveness of maintenance tasks. However, very few studies have focused on understanding developer practices to write comments. None of them has compared such developer practices to the standard comment guidelines to study the extent to which developers follow the guidelines. Objective Therefore, our goal is to investigate developer commenting practices and compare them to the comment guidelines. Method This paper reports the first empirical study investigating commenting practices in Pharo Smalltalk. First, we analyze class comment evolution over seven Pharo versions. Then, we quantitatively and qualitatively investigate the information types embedded in class comments. Finally, we study the adherence of developer commenting practices to the official class comment template over Pharo versions. Results Our results show that there is a rapid increase in class comments in the initial three Pharo versions, while in subsequent versions developers added comments to both new and old classes, thus maintaining a similar code to comment ratio. We furthermore found three times as many information types in class comments as those suggested by the template. However, the information types suggested by the template tend to be present more often than other types of information. Additionally, we find that a substantial proportion of comments follow the writing style of the template in writing these information types, but they are written and formatted in a non-uniform way. Conclusion The results suggest the need to standardize the commenting guidelines for formatting the text, and to provide headers for the different information types to ensure a consistent style and to identify the information easily. Given the importance of high-quality code comments, we draw numerous implications for developers and researchers to improve the support for comment quality assessment tools.

scholarly journals On the use of deep feedforward neural networks for automatic language identification

2016 ◽  
Vol 40 ◽  
pp. 46-59 ◽  
Author(s):  
Ignacio Lopez-Moreno ◽  
Javier Gonzalez-Dominguez ◽  
David Martinez ◽  
Oldřich Plchot ◽  
Joaquin Gonzalez-Rodriguez ◽  
...  
Keyword(s):  
Neural Networks ◽  
Feedforward Neural Networks ◽  
Language Identification

scholarly journals Deep learning-enabled medical computer vision

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Andre Esteva ◽  
Katherine Chou ◽  
Serena Yeung ◽  
Nikhil Naik ◽  
Ali Madani ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Computer Vision ◽  
Deep Learning ◽  
Medical Imaging ◽  
Real World ◽  
Recent Progress ◽  
Medical Applications ◽  
Modern Computer ◽  
Medical Computer

AbstractA decade of unprecedented progress in artificial intelligence (AI) has demonstrated the potential for many fields—including medicine—to benefit from the insights that AI techniques can extract from data. Here we survey recent progress in the development of modern computer vision techniques—powered by deep learning—for medical applications, focusing on medical imaging, medical video, and clinical deployment. We start by briefly summarizing a decade of progress in convolutional neural networks, including the vision tasks they enable, in the context of healthcare. Next, we discuss several example medical imaging applications that stand to benefit—including cardiology, pathology, dermatology, ophthalmology–and propose new avenues for continued work. We then expand into general medical video, highlighting ways in which clinical workflows can integrate computer vision to enhance care. Finally, we discuss the challenges and hurdles required for real-world clinical deployment of these technologies.

Sign in / Sign up

Export Citation Format

Share Document