ActGraph: prioritization of test cases based on deep neural network activation graph
J Chen, J Ge, H Zheng - Automated Software Engineering, 2023 - Springer
Widespread applications of deep neural networks (DNNs) benefit from DNN testing to
guarantee their quality. In the DNN testing, numerous test cases are fed into the model to …
guarantee their quality. In the DNN testing, numerous test cases are fed into the model to …
Backdoor Online Tracing With Evolving Graphs
The backdoor attacks have posed a severe threat to deep neural networks (DNNs). Online
training platforms and third-party model training providers are more vulnerable to backdoor …
training platforms and third-party model training providers are more vulnerable to backdoor …
Harnessing Neural Unit Dynamics for Effective and Scalable Class-Incremental Learning
Class-incremental learning (CIL) aims to train a model to learn new classes from non-
stationary data streams without forgetting old ones. In this paper, we propose a new kind of …
stationary data streams without forgetting old ones. In this paper, we propose a new kind of …
Structure of Artificial Neural Networks--Empirical Investigations
J Stier - arxiv preprint arxiv:2410.09579, 2024 - arxiv.org
Within one decade, Deep Learning overtook the dominating solution methods of countless
problems of artificial intelligence.``Deep''refers to the deep architectures with operations in …
problems of artificial intelligence.``Deep''refers to the deep architectures with operations in …
Peeking inside Sparse Neural Networks using Multi-Partite Graph Representations
Abstract Modern Deep Neural Networks (DNNs) have achieved very high performance at
the expense of computational resources. To decrease the computational burden, several …
the expense of computational resources. To decrease the computational burden, several …