1 code implementation • 21 Jun 2023 • Boyan Li, Luziwei Leng, Shuaijie Shen, Kaixuan Zhang, JianGuo Zhang, Jianxing Liao, Ran Cheng
As a result, we establish an efficient multi-stage spiking MLP network that blends effectively global receptive fields with local feature extraction for comprehensive spike-based computation.
1 code implementation • CVPR 2022 • Kaixuan Zhang, Kaiwei Che, JianGuo Zhang, Jie Cheng, Ziyang Zhang, Qinghai Guo, Luziwei Leng
Inspired by continuous dynamics of biological neuron models, we propose a novel encoding method for sparse events - continuous time convolution (CTC) - which learns to model the spatial feature of the data with intrinsic dynamics.
3 code implementations • 18 Apr 2020 • Zejiang Shen, Kaixuan Zhang, Melissa Dell
Deep learning-based approaches for automatic document layout analysis and content extraction have the potential to unlock rich information trapped in historical documents on a large scale.
1 code implementation • 12 Nov 2019 • Qinglong Wang, Kaixuan Zhang, Xue Liu, C. Lee Giles
We propose an approach that connects recurrent networks with different orders of hidden interaction with regular grammars of different levels of complexity.
no code implementations • 15 Oct 2019 • Kaixuan Zhang, Qinglong Wang, Xue Liu, C. Lee Giles
This has motivated different research areas such as data poisoning, model improvement, and explanation of machine learning models.
no code implementations • NeurIPS Workshop Document_Intelligen 2019 • Kaixuan Zhang, Zejiang Shen, Jie zhou, Melissa Dell
Recent innovations have improved layout analysis of document images, significantly improving our ability to identify text and non-text regions.
no code implementations • 14 Nov 2018 • Qinglong Wang, Kaixuan Zhang, Xue Liu, C. Lee Giles
The verification problem for neural networks is verifying whether a neural network will suffer from adversarial samples, or approximating the maximal allowed scale of adversarial perturbation that can be endured.
no code implementations • 16 Jan 2018 • Qinglong Wang, Kaixuan Zhang, Alexander G. Ororbia II, Xinyu Xing, Xue Liu, C. Lee Giles
Then we empirically evaluate different recurrent networks for their performance of DFA extraction on all Tomita grammars.
no code implementations • 29 Sep 2017 • Qinglong Wang, Kaixuan Zhang, Alexander G. Ororbia II, Xinyu Xing, Xue Liu, C. Lee Giles
Rule extraction from black-box models is critical in domains that require model validation before implementation, as can be the case in credit scoring and medical diagnosis.
no code implementations • 23 May 2017 • Wenbo Guo, Kaixuan Zhang, Lin Lin, Sui Huang, Xinyu Xing
Our results indicate that the proposed approach not only outperforms the state-of-the-art technique in explaining individual decisions but also provides users with an ability to discover the vulnerabilities of a learning model.
no code implementations • 5 Dec 2016 • Qinglong Wang, Wenbo Guo, Kaixuan Zhang, Alexander G. Ororbia II, Xinyu Xing, Xue Liu, C. Lee Giles
Despite the superior performance of DNNs in these applications, it has been recently shown that these models are susceptible to a particular type of attack that exploits a fundamental flaw in their design.
no code implementations • 5 Oct 2016 • Qinglong Wang, Wenbo Guo, Kaixuan Zhang, Alexander G. Ororbia II, Xinyu Xing, C. Lee Giles, Xue Liu
However, after a thorough analysis of the fundamental flaw in DNNs, we discover that the effectiveness of current defenses is limited and, more importantly, cannot provide theoretical guarantees as to their robustness against adversarial sampled-based attacks.