A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Filters
A Survey on Software Defect Prediction Using Deep Learning
2021
Mathematics
Preserved Fulltext
The problem in this area is to properly identify the defective source code with high accuracy. ...
Developing a fault prediction model is a challenging problem, and many approaches have been proposed throughout history. ...
Convolutional Neural Networks The Convolutional Neural Networks [23] are a type of neural network specialized for processing the data with a mesh-like structure. ...
doi:10.3390/math9111180
fatcat:rqpsievq7rcplc7dp3qojyk6le
Deep Learning for Source Code Modeling and Generation: Models, Applications and Challenges
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
To facilitate further research and applications of DL in this field, we provide a comprehensive review to categorize and investigate existing DL methods for source code modeling and generation. ...
Deep Learning (DL) techniques for Natural Language Processing have been evolving remarkably fast. ...
[124] have proposed a novel open-vocabulary neural language model for source code modeling. ...
arXiv:2002.05442v1
fatcat:bt7dtzrcnjfk5jn6kmin2ruqii
Guided code synthesis using deep neural networks
2016
Proceedings of the 2016 24th ACM SIGSOFT International Symposium on Foundations of Software Engineering - FSE 2016
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Recent advances in neural network research reveal that certain neural networks are able not only to learn the syntax, grammar and semantics of arbitrary character sequences, but also synthesize new samples ...
We explore the adaptation of these techniques to code classification, comprehension and completion. ...
Hence, we formulate our primary research question: RQ* How can character-level deep neural networks aid the synthesis of source code for practical applications? ...
doi:10.1145/2950290.2983951
dblp:conf/sigsoft/Alexandru16
fatcat:2tjazzk3wvd7jpiwgrndorwfli
From Programs to Interpretable Deep Models and Back
[chapter]
2018
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
In the second part, we describe techniques for extracting interpretable representations from deep models, shedding light on what has actually been learned in various tasks. E. Yahav-Joint work with ...
We describe a general path-based representation of source code that can be used across programming languages and learning tasks, and discuss how this representation enables different learning algorithms ...
The main idea is a neural network that learns code embeddings -continuous distributed vector representations for code. ...
doi:10.1007/978-3-319-96145-3_2
fatcat:3gbeirslnzebpejhcs3gdam3ji
Toward Deep Learning Software Repositories
2015
2015 IEEE/ACM 12th Working Conference on Mining Software Repositories
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Our deep learning models are applicable to source code files (since they only require lexically analyzed source code written in any programming language) and other types of artifacts. ...
We experiment with two of the models' hyperparameters, which govern their capacity and the amount of context they use to inform predictions, before building several committees of software language models ...
ACKNOWLEDGMENT We would like to thank Abram Hindle from the University of Alberta for sharing his tools and data from his empirical study [5] . ...
doi:10.1109/msr.2015.38
dblp:conf/msr/WhiteVVP15
fatcat:z7hiii7wkfbdjmfzvimpfltbma
Automated Source Code Generation and Auto-completion Using Deep Learning: Comparing and Discussing Current Language-Model-Related Approaches
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2009.07740v3 fatcat:p3sw4unnsvdmhbvihpkvantrniOther Versions
models using a Python dataset for code generation and filling mask tasks. ...
language models based on programming code. ...
Acknowledgments We thank the IBM Quantum team and the IBM Research ETX team for the insightful discussions about this research and the support received during the development of this research. ...
arXiv:2009.07740v4
fatcat:3nae472wkjhd5ejwta33alk5nm
Exploring the use of deep learning for feature location
2015
2015 IEEE International Conference on Software Maintenance and Evolution (ICSME)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Deep learning models are a class of neural networks. Relative to n-gram models, deep learning models can capture more complex statistical patterns based on smaller training corpora. ...
DVs seem well suited to use with source code, because they both capture the influence of context on each term in a corpus and map terms into a continuous semantic space that encodes semantic relationships ...
deep learning neural network encodes source code
identifiers, in the order they appear in the source code, in its
input layer. ...
doi:10.1109/icsm.2015.7332513
dblp:conf/icsm/CorleyDK15
fatcat:4hme63dgnjbzji4vwgg5hqbgum
DeepVS: An Efficient and Generic Approach for Source Code Modeling Usage
2020
Electronics Letters
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Next, for the purpose of neural language model training, we vectorise these extracted contexts. Finally, we train and test the BiGRU classifier for the code completion task. ...
Recently, deep learning-based approaches have shown great potential in the modelling of source code for various software engineering tasks. ...
Then, each code token is replaced with its corresponding vocabulary index (positive integer) to convert context vectors into a form that is suitable for neural language model training. ...
doi:10.1049/el.2020.0500
fatcat:cersfbsgifbszf6vs3u4d75lni
On the Feasibility of Transfer-learning Code Smells using Deep Learning
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Context: A substantial amount of work has been done to detect smells in source code using metrics-based and heuristics-based methods. ...
Second, investigate the possibility of applying transfer-learning in the context of deep learning models for smell detection. ...
This work was supported by computational time granted from the National Infrastructures for Research and Technology s.a. ...
arXiv:1904.03031v2
fatcat:v5yxgteizfdzbitnt32ff7ruoq
On End-to-End Program Generation from User Intention by Deep Neural Networks
[article]
2015
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
code in a characterby-by-character fashion. ...
This paper envisions an end-to-end program generation scenario using recurrent neural networks (RNNs): Users can express their intention in natural language; an RNN then automatically generates corresponding ...
A very powerful machine (e.g., deep neural network) learns the mapping from natural language of problem descriptions to source code. ...
arXiv:1510.07211v1
fatcat:gmmz2vceybe5liqes5ke5f7zxu
Unified Deep Semantic Search on Code
2020
International Journal of Engineering and Advanced Technology
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
While the previous models for code search using deep neural networks do a good job but, most of them only evaluate their models on only a single programming language, mostly Java. ...
In this paper, we propose a novel deep neural network model called Unified Code Net that can handle the intricacies of different programming languages. ...
RELATED WORK Deep Code Search [5] uses a neural network called CODEnn (Code Description Embedding Neural Network) to embed code snippets in high-dimensional vector space. ...
doi:10.35940/ijeat.e9861.069520
fatcat:2ysmnrtpwvfazcwyfunytuys74
A Survey of Automatic Generation of Source Code Comments: Algorithms and Techniques
2019
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
As a result, code comments can be inadequate, absent or even mismatched with source code, which affects the understanding, reusing and the maintenance of software. ...
As an integral part of source code files, code comments help improve program readability and comprehension. ...
In 2015, with the emergence and development of neural network techniques, deep neural network models was first applied to automatic generation of code comments. ...
doi:10.1109/access.2019.2931579
fatcat:gzwjs6wnerec3nlciqmrvpbsz4
Improving source code suggestion with code embedding and enhanced convolutional long short‐term memory
2021
IET Software
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
First, DeepSN uses an enhanced hierarchical convolutional neural network combined with code-embedding to automatically extract the top-notch features of the source code and to learn useful semantic information ...
To improve the performance of source code suggestion, the authors propose a deep semantic net (DeepSN) that makes use of semantic information of the source code. ...
[12] have proposed a syntax-driven neural network for the task of source code generation. Maddison et al. ...
doi:10.1049/sfw2.12017
fatcat:tbk4m3ycarbelnpoetnjpw5jwy
A Context-Aware Neural Embedding for Function-Level Vulnerability Detection
2021
Algorithms
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Based on the evaluation, we propose a supervised framework leveraging pre-trained context-aware embeddings from language models (ELMo) to capture deep contextual representations, further summarized by ...
Most ML techniques aim to isolate a unit of source code, be it a line or a function, as being vulnerable. ...
neural language models to software code analysis [16, 17, 48] . ...
doi:10.3390/a14110335
fatcat:ucs65dzz6bgndddk62lrcxxxgm
Improving automatic source code summarization via deep reinforcement learning
2018
Proceedings of the 33rd ACM/IEEE International Conference on Automated Software Engineering - ASE 2018
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Comprehensive experiments on a real-world dataset show the effectiveness of our proposed model when compared with the state-of-the-art ones. ...
In this paper, we incorporate an abstract syntax tree structure as well as sequential content of code snippets into a deep reinforcement learning framework (i.e., actor-critic network learning). ...
The neural language model is a language model based on neural networks. ...
doi:10.1145/3238147.3238206
dblp:conf/kbse/WanZYXY0Y18
fatcat:eknsug7narft5dre5ncenn2nvm
« Previous
Showing results 1 — 15 out of 35,818 results