Search Results for author: Zhen Liang

Found 11 papers, 4 papers with code

UR4NNV: Neural Network Verification, Under-approximation Reachability Works!

no code implementations23 Jan 2024 Zhen Liang, Taoran Wu, Ran Zhao, Bai Xue, Ji Wang, Wenjing Yang, Shaojun Deng, Wanwei Liu

However, these strategies face challenges in addressing the "unknown dilemma" concerning whether the exact output region or the introduced approximation error violates the property in question.

Semi-Supervised Dual-Stream Self-Attentive Adversarial Graph Contrastive Learning for Cross-Subject EEG-based Emotion Recognition

no code implementations13 Aug 2023 Weishan Ye, Zhiguo Zhang, Min Zhang, Fei Teng, Li Zhang, Linling Li, Gan Huang, Jianhong Wang, Dong Ni, Zhen Liang

In this paper, a semi-supervised Dual-stream Self-Attentive Adversarial Graph Contrastive learning framework (termed as DS-AGC) is proposed to tackle the challenge of limited labeled data in cross-subject EEG-based emotion recognition.

Contrastive Learning Domain Adaptation +2

An Automata-Theoretic Approach to Synthesizing Binarized Neural Networks

no code implementations29 Jul 2023 Ye Tao, Wanwei Liu, Fu Song, Zhen Liang, Ji Wang, Hongxu Zhu

Quantized neural networks (QNNs) have been developed, with binarized neural networks (BNNs) restricted to binary values as a special case.

Fairness Quantization

Verifying Safety of Neural Networks from Topological Perspectives

1 code implementation27 Jun 2023 Zhen Liang, Dejin Ren, Bai Xue, Ji Wang, Wenjing Yang, Wanwei Liu

Moreover, for NNs that do not feature these properties with respect to the input set, we explore subsets of the input set for establishing the local homeomorphism property and then abandon these subsets for reachability computations.

Autonomous Vehicles

Semi-Supervised Learning for Multi-Label Cardiovascular Diseases Prediction:A Multi-Dataset Study

no code implementations18 Jun 2023 Rushuang Zhou, Lei Lu, Zijun Liu, Ting Xiang, Zhen Liang, David A. Clifton, Yining Dong, Yuan-Ting Zhang

However, the label scarcity problem, the co-occurrence of multiple CVDs and the poor performance on unseen datasets greatly hinder the widespread application of deep learning-based models.

Data Augmentation Electrocardiography (ECG) +2

Repairing Deep Neural Networks Based on Behavior Imitation

1 code implementation5 May 2023 Zhen Liang, Taoran Wu, Changyuan Zhao, Wanwei Liu, Bai Xue, Wenjing Yang, Ji Wang

For the fine-tuning repair process, BIRDNN analyzes the behavior differences of neurons on positive and negative samples to identify the most responsible neurons for the erroneous behaviors.

EEGMatch: Learning with Incomplete Labels for Semi-Supervised EEG-based Cross-Subject Emotion Recognition

1 code implementation27 Mar 2023 Rushuang Zhou, Weishan Ye, Zhiguo Zhang, Yanyang Luo, Li Zhang, Linling Li, Gan Huang, Yining Dong, Yuan-Ting Zhang, Zhen Liang

The results show the proposed EEGmatch performs better than the state-of-the-art methods under different incomplete label conditions (with 6. 89% improvement on SEED and 1. 44% improvement on SEED-IV), which demonstrates the effectiveness of the proposed EEGMatch in dealing with the label scarcity problem in emotion recognition using EEG signals.

Data Augmentation Domain Adaptation +3

MassNet: A Deep Learning Approach for Body Weight Extraction from A Single Pressure Image

no code implementations17 Mar 2023 Ziyu Wu, Quan Wan, Mingjie Zhao, Yi Ke, Yiran Fang, Zhen Liang, Fangting Xie, Jingyuan Cheng

To test the model's performance over different hardware and posture settings, we create a pressure image dataset of 10 subjects and 23 postures, using a self-made pressure-sensing bedsheet.

Contrastive Learning Privacy Preserving

Credit Assignment for Trained Neural Networks Based on Koopman Operator Theory

no code implementations2 Dec 2022 Zhen Liang, Changyuan Zhao, Wanwei Liu, Bai Xue, Wenjing Yang, Zhengbin Pang

Based on Koopman operator theory, this paper presents an alternative perspective of linear dynamics on dealing with the credit assignment problem for trained neural networks.

EEGFuseNet: Hybrid Unsupervised Deep Feature Characterization and Fusion for High-Dimensional EEG with An Application to Emotion Recognition

no code implementations7 Feb 2021 Zhen Liang, Rushuang Zhou, Li Zhang, Linling Li, Gan Huang, Zhiguo Zhang, Shin Ishii

The performance of the extracted deep and low-dimensional features by EEGFuseNet is carefully evaluated in an unsupervised emotion recognition application based on three public emotion databases.

EEG Emotion Recognition +2

Cannot find the paper you are looking for? You can Submit a new open access paper.