Related papers: DeepMetis: Augmenting a Deep Learning Test Set to …

We explore the use of multiple deep learning models for detecting flaws in software programs. Current, standard approaches for flaw detection rely on a single representation of a software program (e.g., source code or a program binary). We…

Datasets nowadays are generally constructed from multiple sources and using different synthetic techniques, making data de-noising and de-duplication crucial before being used for post-training. In this work, we propose to perform…

We tackle the challenging issue of aggressive fine-tuning encountered during the process of transfer learning of pre-trained language models (PLMs) with limited labeled downstream data. This problem primarily results in a decline in…

Evaluating software engineering capabilities has become a core component of modern large language models (LLMs); however, the key bottleneck hindering further scaling lies not in the scarcity of high-quality solutions, but in the lack of…

Dynamic ensemble selection (DES) techniques work by estimating the level of competence of each classifier from a pool of classifiers. Only the most competent ones are selected to classify a given test sample. Hence, the key issue in DES is…

Deep neural networks has been increasingly applied in fault diagnostics, where it uses historical data to capture systems behavior, bypassing the need for high-fidelity physical models. However, despite their competence in prediction tasks,…

As more and more artificial intelligence (AI) technologies move from the laboratory to real-world applications, the open-set and robustness challenges brought by data from the real world have received increasing attention. Data augmentation…

Testing the implementation of deep learning systems and their training routines is crucial to maintain a reliable code base. Modern software development employs processes, such as Continuous Integration, in which changes to the software are…

Readability assessment aims to automatically classify text by the level appropriate for learning readers. Traditional approaches to this task utilize a variety of linguistically motivated features paired with simple machine learning models.…

Testing Deep Learning (DL) based systems inherently requires large and representative test sets to evaluate whether DL systems generalise beyond their training datasets. Diverse Test Input Generators (TIGs) have been proposed to produce…

In recent years, laser ultrasonic visualization testing (LUVT) has attracted much attention because of its ability to efficiently perform non-contact ultrasonic non-destructive testing.Despite many success reports of deep learning based…

Large Language Models (LLMs) often fail to generate correct code on the first attempt, which requires using generated unit tests as verifiers to validate the solutions. Despite the success of recent verification methods, they remain…

In the context of classification problems, Deep Learning (DL) approaches represent state of art. Many DL approaches are based on variations of standard multi-layer feed-forward neural networks. These are also referred to as deep networks.…

This paper introduces an integrated system designed to enhance the explainability of fault diagnostics in complex systems, such as nuclear power plants, where operator understanding is critical for informed decision-making. By combining a…

Semantic-based test generators are widely used to produce failure-inducing inputs for Deep Learning (DL) systems. They typically generate challenging test inputs by applying random perturbations to input semantic concepts until a failure is…

This dissertation explores the impact of bias in deep neural networks and presents methods for reducing its influence on model performance. The first part begins by categorizing and describing potential sources of bias and errors in data…

We demonstrate that LLMs may learn indicators of document usefulness and modulate their updates accordingly. We introduce random strings ("tags") as indicators of usefulness in a synthetic fine-tuning dataset. Fine-tuning on this dataset…

Digital systems find it challenging to keep up with cybersecurity threats. The daily emergence of more than 560,000 new malware strains poses significant hazards to the digital ecosystem. The traditional malware detection methods fail to…

Deep learning (DL) is one of the fastest growing topics in materials data science, with rapidly emerging applications spanning atomistic, image-based, spectral, and textual data modalities. DL allows analysis of unstructured data and…

Due to its powerful automatic feature extraction, deep learning (DL) has been widely used in source code vulnerability detection. However, although it performs well on artificial datasets, its performance is not satisfactory when detecting…