Making the Most of Scarce Input Data in Deep Learning-Based Source Code Classification for Heterogeneous Device Mapping.
Emanuele ParisiFrancesco BarchiAndrea BartoliniAndrea AcquavivaPublished in: IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. (2022)
Keyphrases
- source code
- deep learning
- input data
- unsupervised learning
- software systems
- open source
- software maintenance
- machine learning
- data sets
- restricted boltzmann machine
- image data
- decision trees
- plagiarism detection
- software evolution
- software projects
- feature vectors
- text classification
- pattern recognition
- free software
- image classification
- feature extraction
- supervised learning
- program understanding
- image segmentation
- support vector machine
- text files
- artificial intelligence
- software repositories
- high level
- software development
- support vector
- input image
- software engineering
- training set
- feature space