Recently, there has been a significant growth of interest in applying software engineering
techniques for the quality assurance of deep learning (DL) systems. One popular direction is …

Transfer learning is a popular software reuse technique in the deep learning community that
enables developers to build custom models (students) based on sophisticated pretrained …

As the complexity of autonomous vehicles (AVs) continues to increase and artificial
intelligence algorithms are becoming increasingly ubiquitous, a novel safety concern known …

Machine learning (ML) cloud APIs enable developers to easily incorporate learning
solutions into software systems. Unfortunately, ML APIs are challenging to use correctly and …

An increasing number of software applications incorporate machine learning (ML) solutions
for cognitive tasks that statistically mimic human behaviors. To test such software …

Deep neural network (DNN) models, including those used in safety-critical domains, need to
be thoroughly tested to ensure that they can reliably perform well in different scenarios. In …

Deep Learning (DL) components are routinely integrated into software systems that need to
perform complex tasks such as image or natural language processing. The adequacy of the …

It is important to test convolutional neural networks (CNNs) to identify defects (eg error-
inducing inputs) before deploying them in security-sensitive scenarios. Although existing …

Deep neural networks (DNNs) have demonstrated superior performance over classical
machine learning to support many features in safety-critical systems. Although DNNs are …

The unprecedented advancement of artificial intelligence (AI) in recent years has altered our
perspectives on software engineering and systems engineering as a whole. Nowadays …