[HTML][HTML] A review of uncertainty quantification in deep learning: Techniques, applications and challenges

M Abdar, F Pourpanah, S Hussain, D Rezazadegan… - Information fusion, 2021 - Elsevier
Uncertainty quantification (UQ) methods play a pivotal role in reducing the impact of
uncertainties during both optimization and decision making processes. They have been …

Software engineering for AI-based systems: a survey

S Martínez-Fernández, J Bogner, X Franch… - ACM Transactions on …, 2022 - dl.acm.org
AI-based systems are software systems with functionalities enabled by at least one AI
component (eg, for image-, speech-recognition, and autonomous driving). AI-based systems …

Deephunter: a coverage-guided fuzz testing framework for deep neural networks

X Xie, L Ma, F Juefei-Xu, M Xue, H Chen, Y Liu… - Proceedings of the 28th …, 2019 - dl.acm.org
The past decade has seen the great potential of applying deep neural network (DNN) based
software to safety-critical scenarios, such as autonomous driving. Similar to traditional …

Retrieval-augmented generation for code summarization via hybrid gnn

S Liu, Y Chen, X Xie, J Siow, Y Liu - arXiv preprint arXiv:2006.05405, 2020 - arxiv.org
Source code summarization aims to generate natural language summaries from structured
code snippets for better understanding code functionalities. However, automatic code …

Wuji: Automatic online combat game testing using evolutionary deep reinforcement learning

Y Zheng, X Xie, T Su, L Ma, J Hao… - 2019 34th IEEE/ACM …, 2019 - ieeexplore.ieee.org
Game testing has been long recognized as a notoriously challenging task, which mainly
relies on manual playing and scripting based testing in game industry. Even until recently …

Deepstellar: Model-based quantitative analysis of stateful deep learning systems

X Du, X Xie, Y Li, L Ma, Y Liu, J Zhao - … of the 2019 27th ACM Joint …, 2019 - dl.acm.org
Deep Learning (DL) has achieved tremendous success in many cutting-edge applications.
However, the state-of-the-art DL systems still suffer from quality issues. While some recent …

An empirical study of common challenges in developing deep learning applications

T Zhang, C Gao, L Ma, M Lyu… - 2019 IEEE 30th …, 2019 - ieeexplore.ieee.org
Recent advances in deep learning promote the innovation of many intelligent systems and
applications such as autonomous driving and image recognition. Despite enormous efforts …

Efficientderain: Learning pixel-wise dilation filtering for high-efficiency single-image deraining

Q Guo, J Sun, F Juefei-Xu, L Ma, X Xie… - Proceedings of the …, 2021 - ojs.aaai.org
Single-image deraining is rather challenging due to the unknown rain model. Existing
methods often make specific assumptions of the rain model, which can hardly cover many …

A performance-sensitive malware detection system using deep learning on mobile devices

R Feng, S Chen, X Xie, G Meng… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Currently, Android malware detection is mostly performed on server side against the
increasing number of malware. Powerful computing resource provides more exhaustive …

An empirical study towards characterizing deep learning development and deployment across different frameworks and platforms

Q Guo, S Chen, X Xie, L Ma, Q Hu, H Liu… - 2019 34th IEEE/ACM …, 2019 - ieeexplore.ieee.org
Deep Learning (DL) has recently achieved tremendous success. A variety of DL frameworks
and platforms play a key role to catalyze such progress. However, the differences in …