Source code change analysis with deep learning based programming model

2022 ◽  
Vol 29 (1) ◽  
Author(s):  
Babita Pathik ◽  
Meena Sharma
Keyword(s):  
Deep Learning ◽  
Programming Model ◽  
Source Code ◽  
Change Analysis ◽  
Code Change

Literature survey of deep learning-based vulnerability analysis on source code

IET Software ◽  
2020 ◽  
Vol 14 (6) ◽  
pp. 654-664
Author(s):  
Abubakar Omari Abdallah Semasaba ◽  
Wei Zheng ◽  
Xiaoxue Wu ◽  
Samuel Akwasi Agyemang
Keyword(s):  
Deep Learning ◽  
Source Code ◽  
Vulnerability Analysis ◽  
Literature Survey

scholarly journals Encoding Health Records into Pathway Representations for Deep Learning

2021 ◽  
Author(s):  
Marco Luca Sbodio ◽  
Natasha Mulligan ◽  
Stefanie Speichert ◽  
Vanessa Lopez ◽  
Joao Bettencourt-Silva
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Source Code ◽  
Training Dataset ◽  
Health Records ◽  
Learning Tasks ◽  
Patient Pathways ◽  
Computational Resources ◽  
The Impact

There is a growing trend in building deep learning patient representations from health records to obtain a comprehensive view of a patient’s data for machine learning tasks. This paper proposes a reproducible approach to generate patient pathways from health records and to transform them into a machine-processable image-like structure useful for deep learning tasks. Based on this approach, we generated over a million pathways from FAIR synthetic health records and used them to train a convolutional neural network. Our initial experiments show the accuracy of the CNN on a prediction task is comparable or better than other autoencoders trained on the same data, while requiring significantly less computational resources for training. We also assess the impact of the size of the training dataset on autoencoders performances. The source code for generating pathways from health records is provided as open source.

scholarly journals AtLoc: Attention Guided Camera Localization

2020 ◽  
Vol 34 (06) ◽  
pp. 10393-10401
Author(s):  
Bing Wang ◽  
Changhao Chen ◽  
Chris Xiaoxuan Lu ◽  
Peijun Zhao ◽  
Niki Trigoni ◽  
...  
Keyword(s):  
Deep Learning ◽  
Experimental Evidence ◽  
State Of The Art ◽  
Source Code ◽  
Single Image ◽  
Saliency Maps ◽  
Camera Localization ◽  
Camera Pose ◽  
Dynamic Objects ◽  
Indoor And Outdoor

Deep learning has achieved impressive results in camera localization, but current single-image techniques typically suffer from a lack of robustness, leading to large outliers. To some extent, this has been tackled by sequential (multi-images) or geometry constraint approaches, which can learn to reject dynamic objects and illumination conditions to achieve better performance. In this work, we show that attention can be used to force the network to focus on more geometrically robust objects and features, achieving state-of-the-art performance in common benchmark, even if using only a single image as input. Extensive experimental evidence is provided through public indoor and outdoor datasets. Through visualization of the saliency maps, we demonstrate how the network learns to reject dynamic objects, yielding superior global camera pose regression performance. The source code is avaliable at https://github.com/BingCS/AtLoc.

Imposing Contiguity Constraints in Political Districting Models

2021 ◽  
Author(s):  
Hamidreza Validi ◽  
Austin Buchanan ◽  
Eugene Lykhovyd
Keyword(s):  
Integer Programming ◽  
Operations Research ◽  
Programming Model ◽  
A Priori ◽  
Source Code ◽  
Branch And Cut ◽  
Computer Implementation ◽  
Census Tracts ◽  
Integer Programming Model ◽  
Political Districting

For nearly 60 years, operations research techniques have assisted in the creation of political districting plans, beginning with an integer programming model. This model, which seeks compactness as its objective, tends to generate districts that are contiguous, or nearly so, but provides no guarantee of contiguity. In the paper “Imposing contiguity constraints in political districting models” by Hamidreza Validi, Austin Buchanan, and Eugene Lykhovyd, the authors consider and analyze four different contiguity models (two old and two new). Their computer implementation can handle redistricting instances as large as Indiana (1,511 census tracts). Their fastest approach uses a branch-and-cut algorithm, where contiguity constraints are added in a callback. Critically, many variables can be fixed to zero a priori by Lagrangian arguments. All test instances and source code are publicly available.

Detecting and Fixing Nonidiomatic Snippets in Python Source Code with Deep Learning

2021 ◽  
pp. 129-147
Author(s):  
Balázs Szalontai ◽  
András Vadász ◽  
Zsolt Richárd Borsi ◽  
Teréz A. Várkonyi ◽  
Balázs Pintér ◽  
...  
Keyword(s):  
Deep Learning ◽  
Source Code

Source code-based defect prediction using deep learning and transfer learning

2019 ◽  
Vol 23 (6) ◽  
pp. 1243-1269
Author(s):  
Ahmad A. Saifan ◽  
Nawzat Al Smadi
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
Source Code ◽  
Defect Prediction

scholarly journals Deep Transfer Learning for Source Code Modeling

2020 ◽  
Vol 30 (05) ◽  
pp. 649-668
Author(s):  
Yasir Hussain ◽  
Zhiqiu Huang ◽  
Yu Zhou ◽  
Senzhang Wang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Transfer Learning ◽  
Related Problem ◽  
State Of The Art ◽  
Source Code ◽  
Traditional Learning ◽  
Learning Models ◽  
Modeling And Analysis ◽  
F Measure

In recent years, deep learning models have shown great potential in source code modeling and analysis. Generally, deep learning-based approaches are problem-specific and data-hungry. A challenging issue of these approaches is that they require training from scratch for a different related problem. In this work, we propose a transfer learning-based approach that significantly improves the performance of deep learning-based source code models. In contrast to traditional learning paradigms, transfer learning can transfer the knowledge learned in solving one problem into another related problem. First, we present two recurrent neural network-based models RNN and GRU for the purpose of transfer learning in the domain of source code modeling. Next, via transfer learning, these pre-trained (RNN and GRU) models are used as feature extractors. Then, these extracted features are combined into attention learner for different downstream tasks. The attention learner leverages from the learned knowledge of pre-trained models and fine-tunes them for a specific downstream task. We evaluate the performance of the proposed approach with extensive experiments with the source code suggestion task. The results indicate that the proposed approach outperforms the state-of-the-art models in terms of accuracy, precision, recall and F-measure without training the models from scratch.

Sign in / Sign up

Export Citation Format

Share Document