检索结果-内蒙古大学图书馆

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Rui Liu Wenguan Wang Yi Yang The State Key Lab of Brain-Machine Intelligence and College of Computer Science and Technology Zhejiang University Hangzhou China College of Computer Science and Technology Zhejiang University Hangzhou China

ISBN: (纸本)9798331314385

Vision-language navigation (VLN) requires an agent to execute actions following human instructions. Existing VLN models are optimized through expert demonstrations by supervised behavioural cloning or incorporating manual reward engineering. While straightforward, these efforts overlook the accumulation of errors in the Markov decision process, and struggle to match the distribution of the expert policy. Going beyond this, we propose an Energy-based Navigation Policy (ENP) to model the joint state-action distribution using an energy-based model. At each step, low energy values correspond to the state-action pairs that the expert is most likely to perform, and vice versa. Theoretically, the optimization objective is equivalent to minimizing the forward divergence between the occupancy measure of the expert and ours. Consequently, ENP learns to globally align with the expert policy by maximizing the likelihood of the actions and modeling the dynamics of the navigation states in a collaborative manner. With a variety of VLN architectures, ENP achieves promising performances on R2R, REVERIE, RxR, and R2R-CE, unleashing the power of existing VLN models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Battery-Free Wireless Temperature Sensing Chip for Food Monitoring

A Battery-Free Wireless Temperature Sensing Chip for Food Mo...

引用

2024 IEEE International Conference on Integrated Circuits, Technologies and Applications, ICTA 2024

作者： Wang, Jiayi Li, Haoyang Wang, Weixiao Fang, Tianying Li, Jiaqing Luo, Yuxuan Zhao, Bo Zhejiang University College of Integrated Circuits Hangzhou China Nanhu Brian-Computer Interface Institute Hangzhou China Zhejiang University The State Key Lab of Brain-Machine Intelligence Hangzhou China

ISBN: (纸本)9798331530709

This work presents a battery-free wireless temperature sensing chip for long-termly monitoring the food production environment. A calibrated oscillator-based CMOS temperature sensor is proposed instead of the ADC-based power-hungry circuits in conventional works. In addition, the sensor chip can harvest the power transferred by a remote reader to eliminate the use of battery. Meanwhile, the system conduct wireless bidirectional communication between the sensor chip and reader. In this way, the temperature sensing chip is fabricated in 55 nm CMOS process, and the reader chip is implemented in 65 nm CMOS technology. Experimental results show that the temperature measurement error achieves ± 1.6 ° C from 25 ° C to 50 ° C, with battery-free readout by a remote reader. © 2024 IEEE.

关键词： CMOS integrated circuits

来源：评论

学校读者我要写书评

暂无评论

Rethinking the membrane dynamics and optimization objectives of spiking neural networks 24

Rethinking the membrane dynamics and optimization objectives...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Hangchi Shen Qian Zheng Huamin Wang Gang Pan College of Artificial Intelligence Southwest University and Chongqing Key Laboratory of Brain Inspired Computing and Intelligent Chips The State Key Lab of Brain-Machine Intelligence and College of Computer Science and Technology Zhejiang University

ISBN: (纸本)9798331314385

Despite spiking neural networks (SNNs) have demonstrated notable energy efficiency across various fields, the limited firing patterns of spiking neurons within fixed time steps restrict the expression of information, which impedes further improvement of SNN performance. In addition, current implementations of SNNs typically consider the firing rate or average membrane potential of the last layer as the output, lacking exploration of other possibilities. In this paper, we identify that the limited spike patterns of spiking neurons stem from the initial membrane potential (IMP), which is set to 0. By adjusting the IMP, the spiking neurons can generate additional firing patterns and pattern mappings. Furthermore, we find that in static tasks, the accuracy of SNNs at each time step increases as the membrane potential evolves from zero. This observation inspires us to propose a learnable IMP, which can accelerate the evolution of membrane potential and enables higher performance within a limited number of time steps. Additionally, we introduce the last time step (LTS) approach to accelerate convergence in static tasks, and we propose a label smooth temporal efficient training (TET) loss to mitigate the conflicts between optimization objective and regularization term in the vanilla TET. Our methods improve the accuracy by 4.05% on ImageNet compared to baseline and achieve state-of-the-art performance of 87.80% on CIFAR10-DVS and 87.86% on N-Caltech101. The code is available at https://***/StephenTaylor1998/IMP-SNN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DeepGCN based on variable multi‐graph and multimodal data for ASD diagnosis

引用

CAAI Transactions on intelligence technology 2024年第4期9卷 879-893页

作者： Shuaiqi Liu Siqi Wang Chaolei Sun Bing Li Shuihua Wang Fei Li College of Electronic and Information Engineering Hebei UniversityBaodingChina Machine Vision Technology Innovation Center of Hebei Province BaodingChina The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijingChina School of Computer Science and Technology Henan Polytechnic UniversityJiaozuoChina

Diagnosing individuals with autism spectrum disorder(ASD)accurately faces great chal-lenges in clinical practice,primarily due to the data's high heterogeneity and limited sample *** tackle this issue,the authors constructed a deep graph convolutional network(GCN)based on variable multi‐graph and multimodal data(VMM‐DGCN)for ASD ***,the functional connectivity matrix was constructed to extract primary ***,the authors constructed a variable multi‐graph construction strategy to capture the multi‐scale feature representations of each subject by utilising convolutional filters with varying kernel ***,the authors brought the non‐imaging in-formation into the feature representation at each scale and constructed multiple population graphs based on multimodal data by fully considering the correlation between *** extracting the deeper features of population graphs using the deep GCN(DeepGCN),the authors fused the node features of multiple subgraphs to perform node classification tasks for typical control and ASD *** proposed algorithm was evaluated on the Autism brain Imaging Data Exchange I(ABIDE I)dataset,achieving an accuracy of 91.62%and an area under the curve value of 95.74%.These results demon-strated its outstanding performance compared to other ASD diagnostic algorithms.

关键词： machine learning medical image processing medical signal processing

来源：评论

学校读者我要写书评

暂无评论

state-sensitive convolutional sparse coding for potential biomarker identification in brain signals

引用

science China(Information sciences) 2024年第5期67卷 270-286页

作者： Puli WANG Yu QI Gang PAN College of Computer Science and Technology Zhejiang University State Key Laboratory of Brain-Machine Intelligence Zhejiang University MOE Frontier Science Center for Brain Science and Brain-machine Integration Zhejiang University Affiliated Mental Health Center & Hangzhou Seventh People's Hospital Zhejiang University School of Medicine

The identification of prototypical waveforms, such as sleep spindles and epileptic spikes, is crucial for the diagnosis of neurological disorders. These prototypical waveforms are usually recurrently presented in certain brain states, serving as potential biomarkers for clinical evaluations. Convolutional sparse coding(CSC) approaches have demonstrated strength in identifying recurrent patterns in time-series. However,existing CSC approaches do not explicitly explore state-specific patterns, making it difficult to identify state-related biomarkers. To address this problem, we propose state-sensitive CSC to learn state-specific prototypical waveforms. Specifically, we model signals of a certain state with specific waveforms that only appear frequently in this state and background waveforms that are independent of states. Based on this,state-sensitive CSC separates state-specific waveforms from background ones explicitly by incorporating incoherence constraints into optimizations. Experiments with epilepsy brain signals demonstrate that our approach can effectively identify prototypical waveforms in pre-ictal states, providing potential biomarkers for seizure prediction. Our approach provides a promising tool for automatic biomarker candidate identification.

关键词： convolutional sparse coding prototypical waveforms state-specific dictionary biomarker identification neural signal processing

来源：评论

学校读者我要写书评

暂无评论

GRSN: Gated Recurrent Spiking Neurons for POMDPs and MARL 39

GRSN: Gated Recurrent Spiking Neurons for POMDPs and MARL

引用

39th Annual AAAI Conference on Artificial intelligence, AAAI 2025

作者： Qin, Lang Wang, Ziming Jiang, Runhao Yan, Rui Tang, Huajin College of Computer Science and Technology Zhejiang University China The State Key Lab of Brain-Machine Intelligence Zhejiang University China College of Computer Science and Technology Zhejiang University of Technology China MOE Frontier Science Center for Brain Science and Brain-Machine Integration Zhejiang University China

ISBN: (纸本)157735897X

Spiking neural networks (SNNs) are widely applied in various fields due to their energy-efficient and fast-inference capabilities. Applying SNNs to reinforcement learning (RL) can significantly reduce the computational resource requirements for agents and improve the algorithm's performance under resource-constrained conditions. However, in current spiking reinforcement learning (SRL) algorithms, the simulation results of multiple time steps can only correspond to a single-step decision in RL. This is quite different from the real temporal dynamics in the brain and also fails to fully exploit the capacity of SNNs to process temporal data. In order to address this temporal mismatch issue and further take advantage of the inherent temporal dynamics of spiking neurons, we propose a novel temporal alignment paradigm (TAP) that leverages the single-step update of spiking neurons to accumulate historical state information in RL and introduces gated units to enhance the memory capacity of spiking neurons. Experimental results show that our method can solve partially observable Markov decision processes (POMDPs) and multi-agent cooperation problems with similar performance as recurrent neural networks (RNNs) but with about 50% power consumption. Copyright © 2025, Association for the Advancement of Artificial intelligence (***). All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

EvHDR-NeRF: Building High Dynamic Range Radiance Fields with Single Exposure Images and Events 39

EvHDR-NeRF: Building High Dynamic Range Radiance Fields with...

引用

39th Annual AAAI Conference on Artificial intelligence, AAAI 2025

作者： Chen, Zehao Liao, Zhanfeng Ma, De Tang, Huajin Zheng, Qian Pan, Gang The State Key Lab of Brain-Machine Intelligence Zhejiang University Hangzhou China College of Computer Science and Technology Zhejiang University Hangzhou China

ISBN: (纸本)157735897X

We present EvHDR-NeRF to recover a High Dynamic Range (HDR) radiance field from event streams and a set of Low Dynamic Range (LDR) views with single exposures. Using the EvHDR-NeRF, we can generate both novel HDR views and novel LDR views under different exposures. The key to our method is to model the new relationship between events streams and LDR images, which considers both the Camera Response Function (CRF) and exposure time. Based on this relationship, we categorize events into inter-frame events and intra-exposure. The former is utilized for building HDR radiance field and the latter is used to deblur potentially blurred images. Compared to existing methods, this method can effectively reconstruct the HDR radiance field even when the input images are degraded. Experimental results demonstrate that our method achieves state-of-the-art HDR reconstruction, providing a more adaptable and accurate solution for complex imaging applications. © 2025, Association for the Advancement of Artificial intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MindGPT: Interpreting What You See with Non-invasive brain Recordings

引用

IEEE Transactions on Image Processing 2025年 34卷 3281-3293页

作者： Chen, Jiaxuan Qi, Yu Wang, Yueming Pan, Gang Zhejiang Unversity State Key Lab of Brain-Machine Intelligence College of Computer Science and Technology Hangzhou 310027 China Zhejiang University MOE Frontier Science Center for Brain Science and Brain-Machine Integration Hangzhou 310027 China Zhejiang University Qiushi Academy for Advanced Studies Hangzhou 310027 China

Decoding of seen visual contents with non-invasive brain recordings has important scientific and practical values. Efforts have been made to recover the seen images from brain signals. However, most existing approaches cannot faithfully reflect the visual contents due to insufficient image quality or semantic mismatches. Compared with reconstructing pixel-level visual images, speaking is a more efficient and effective way to explain visual information. Here we introduce a non-invasive neural decoder, termed MindGPT, which interprets perceived visual stimuli into natural languages from functional Magnetic Resonance Imaging (fMRI) signals in an end-to-end manner. Specifically, our model builds upon a visually guided neural encoder with a cross-attention mechanism. By the collaborative use of data augmentation techniques, this architecture permits us to guide latent neural representations towards a desired language semantic direction in a self-supervised fashion. Through doing so, we found that the neural representations of the MindGPT are explainable, which can be used to evaluate the contributions of visual properties to language semantics. Our experiments show that the generated word sequences truthfully represented the visual information (with essential details) conveyed in the seen stimuli. The results also suggested that with respect to language decoding tasks, the higher visual cortex (HVC) is more semantically informative than the lower visual cortex (LVC), and using only the HVC can recover most of the semantic information. © 1992-2012 IEEE.

关键词： functional Magnetic Resonance Imaging Multimodal representation learning Neural decoding Self-supervised learning Text reconstruction

来源：评论

学校读者我要写书评

暂无评论

Differentiable and Scalable Generative Adversarial Models for Data Imputation (Extended Abstract) 40

Differentiable and Scalable Generative Adversarial Models fo...

引用

40th IEEE International Conference on Data Engineering, ICDE 2024

作者： Wu, Yangyang Wang, Jun Miao, Xiaoye Wang, Wenjia Yin, Jianwei Software College Zhejiang University Ningbo China Academy of Interdisciplinary Studies The Hong Kong University of Science and Technology Hong Kong Hong Kong Center for Data Science Zhejiang University Hangzhou China The State Key Lab of Brain-Machine Intelligence Zhejiang University Hangzhou China Guangzhou China College of Computer Science Zhejiang University Hangzhou China

ISBN: (纸本)9798350317152

The dramatically increasing volume of incomplete data makes the imputation models computationally infeasible in many real-life applications. In this paper, we propose an effective scalable imputation system named SCIS to significantly speed up the training of the differentiable generative adversarial imputation models under accuracy-guarantees for large-scale incomplete data. SCIS consists of two modules, differentiable imputation modeling (DIM) and sample size estimation (SSE). DIM leverages a new masking Sinkhorn divergence function to make an arbitrary generative adversarial imputation model differentiable, while for such a differentiable imputation model, SSE can estimate an appropriate sample size to ensure the user-specified imputation accuracy of the final model. Moreover, SCIS can also accelerate the autoencoder based imputation models. Extensive experiments upon several real-life large-scale datasets demonstrate that, our proposed system can accelerate the generative adversarial model training by 6.23x. Using around 1.27% samples, SCIS yields competitive accuracy with the state-of-the-art imputation methods in much shorter computation time. © 2024 IEEE.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

DRIP: unleashing diffusion priors for joint foreground and alpha prediction in image matting 24

DRIP: unleashing diffusion priors for joint foreground and a...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Xiaodi Li Zongxin Yang Ruijie Quan Yi Yang The State Key Lab of Brain-Machine Intelligence and CCAI College of Computer Science and Technology Zhejiang University Hangzhou China DBMI HMS Harvard University Boston

ISBN: (纸本)9798331314385

Recovering the foreground color and opacity/alpha matte from a single image (i.e., image matting) is a challenging and ill-posed problem where data priors play a critical role in achieving precise results. Due to the limited matting datasets, traditional methods usually struggle to produce high-quality estimation. To address this, we explore the potential of leveraging vision priors embedded in pre-trained latent diffusion models (LDM) for estimating foreground RGBA values in challenging scenarios and rare objects. We introduce Drip, a novel approach for image matting that harnesses the rich prior knowledge of LDM models. Our method incorporates a switcher and a cross-domain attention mechanism to extend the original LDM for joint prediction of the foreground color and opacity. This setup facilitates mutual information exchange and ensures high consistency across both modalities. To mitigate the inherent reconstruction errors of the LDM's VAE decoder, we propose a latent transparency decoder to align the RGBA prediction with the input image, thereby reducing discrepancies. Comprehensive experimental results demonstrate that our approach achieves state-of-the-art performance in foreground and alpha predictions and shows remarkable generalizability across various benchmarks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：