检索结果-内蒙古大学图书馆

Adaptive Domain Alignment Neural Networks for Cross-Domain EEG Emotion Recognition

IEEE Transactions on Affective Computing 2024年第2期16卷 903-914页

作者： Hong, Xuezhu Du, Changde He, Huiguang Chinese Academy of Sciences Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology Institute of Automation Beijing100190 China School of Artificial Intelligence Beijing100049 China

Electroencephalography (EEG) - based Emotion recognition is now facing great challenge of the intra- and inter-subject variability of EEG signal. Researchers attempted to handle this challenge by using transfer learning methods which usually share two main limitations: most of these methods align marginal distributions instead of conditional distributions of source and target data, making the alignment process classwise ambiguous;also, they prefer to use Multi-Layer Perceptron (MLP) with redundant parameters as classifiers, which is shown by recent research that could result serious over-fitting towards labeled data and prevent the model to draw a proper representation space. In our work, we propose a novel domain alignment method: Adaptive Domain Alignment Neural Networks (ADANN). Our method directly model conditional distributions of source and target domains by two sets of label-wise prototypes, representing the density maximum of each class, while the normalized correspond similarity naturally represents the conditional probability. The predicted label for a sample is given by the argument maxima of similarities and therefore the MLP classifier is not required. Using context-instance contrastive learning to align two sets of prototypes, their corresponding conditional distributions are being learned simultaneously. Exhaustive cross-domain experiments have been conducted under protocols that are strongly related to practical application scenarios and our proposed method achieves better or similar performance compared with recent state-of-the-art methods. © 2010-2012 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Single-neuron projectome-guided analysis reveals the neural circuit mechanism underlying endogenous opioid antinociception

引用

National Science Review 2024年第7期11卷 106-125页

作者： Yan-Nong Dou Yuan Liu Wen-Qun Ding Qing Li Hua Zhou Ling Li Meng-Ting Zhao Zheng-Yi-Qi Li Jing Yuan Xiao-Fei Wang Wang-Yuan Zou Anan Li Yan-Gang Sun Institute of Neuroscience Key Laboratory of Brain Cognition and Brain-Inspired Intelligence Technology CAS Center for Excellence in Brain Science&Intelligence Technology Chinese Academy of Sciences Department of Biology School of Life Science and TechnologyShanghaiTech University Lingang Laboratory University of Chinese Academy of Sciences Britton Chance Center for Biomedical Photonics Wuhan National Laboratory for OptoelectronicsMoE Key Laboratory for Biomedical Photonics Huazhong University of Science and Technology Department of Anesthesiology Xiangya HospitalCentral South University HUST-Suzhou Institute for Brainsmatics JITRI

Endogenous opioid antinociception is a self-regulatory mechanism that reduces chronic pain, but its underlying circuit mechanism remains largely unknown. Here, we showed that endogenous opioid antinociception required the activation of mu-opioid receptors（MORs） in GABAergic neurons of the central amygdala nucleus（CEA） in a persistent-hyperalgesia mouse model. Pharmacogenetic suppression of these CEAMORneurons, which mimics the effect of MOR activation, alleviated the persistent ***, single-neuron projection analysis revealed multiple projectome-based subtypes of CEAMORneurons, each innervating distinct target brain regions. We found that the suppression of axon branches projecting to the parabrachial nucleus（PB） of one subtype of CEAMORneurons alleviated persistent hyperalgesia, indicating a subtype-and axonal-branch-specific mechanism of action. Further electrophysiological analysis revealed that suppression of a distinct CEA-PB disinhibitory circuit controlled endogenous opioid antinociception. Thus, this study identified the central neural circuit that underlies endogenous opioid antinociception, providing new insight into the endogenous pain modulatory mechanisms.

关键词： endogenous opioid antinociception mu-opioid receptors central amygdala nucleus parabrachial nucleus single-neuron projectome

来源：评论

学校读者我要写书评

暂无评论

The Insular Cortex:An Interface Between Sensation,Emotion and cognition

引用

Neuroscience Bulletin 2024年第11期40卷 1763-1773页

作者： Ruohan Zhang Hanfei Deng Xiong Xiao Institute of Neuroscience Key Laboratory of Brain Cognition and Brain-inspired Intelligence TechnologyCAS Center for Excellence in Brain Science and Intelligence TechnologyChinese Academy of SciencesShanghai200031China University of Chinese Academy of Sciences Shanghai200031China State Key Laboratory of Medical Neurobiology MOE Frontiers Center for Brain Science and Institutes of Brain ScienceFudan UniversityShanghai200032China

The insula is a complex brain region central to the orchestration of taste perception,interoception,emotion,and *** research has shed light on the intricate connections between the insula and other brain regions,revealing the crucial role of this area in integrating sensory,emotional,and cognitive *** unique anatomical position and extensive connectivity allow the insula to serve as a critical hub in the functional network of the *** summarize its role in interoceptive and exteroceptive sensory processing,illustrating insular function as a bridge connecting internal and external *** on recent research,we delineate the insular involvement in emotional processes,highlighting its implications in psychiatric conditions,such as anxiety,depression,and *** further discuss the insular contributions to cognition,focusing on its significant roles in time perception and ***,the evidence underscores the insular function as a dynamic interface that synthesizes diverse inputs into coherent subjective experiences and decision-making *** this review,we hope to highlight the importance of the insula as an interface between sensation,emotion,and cognition,and to inspire further research into this fascinating brain region.

关键词： Insular cortex Interoception Emotion Reward-Timing Decision making

来源：评论

学校读者我要写书评

暂无评论

Whole-brain Mapping of Inputs and Outputs of Specific Orbitofrontal Cortical Neurons in Mice

引用

Neuroscience Bulletin 2024年第11期40卷 1681-1698页

作者： Yijie Zhang Wen Zhang Lizhao Wang Dechen Liu Taorong Xie Ziwei Le Xiangning Li Hui Gong Xiao-Hong Xu Min Xu Haishan Yao Institute of Neuroscience State Key Laboratory of NeuroscienceCAS Center for Excellence in Brain Science and Intelligence TechnologyChinese Academy of SciencesShanghai200031China University of Chinese Academy of Sciences Beijing100049China HUST-Suzhou Institute for Brainsmatics JITRISuzhou215123China CAS Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of SciencesShanghai200031China Shanghai Center for Brain Science and Brain-Inspired Intelligence Technology Shanghai201210China Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology Shanghai200031China

The orbitofrontal cortex(ORB),a region crucial for stimulus-reward association,decision-making,and flexible behaviors,extensively connects with other brain ***,brain-wide inputs to projection-defined ORB neurons and the distribution of inhibitory neurons postsynaptic to neurons in specific ORB subregions remain poorly *** we mapped the inputs of five types of projection-specific ORB neurons and ORB outputs to two types of inhibitory *** found that different projection-defined ORB neurons received inputs from similar cortical and thalamic regions,albeit with quantitative variations,particularly in somatomotor areas and medial groups of the dorsal *** counting parvalbumin(PV)or somatostatin(SST)interneurons innervated by neurons in specific ORB subregions,we found a higher fraction of PV neurons in sensory cortices and a higher fraction of SST neurons in subcortical regions targeted by medial ORB *** results provide insights into understanding and investigating the function of specific ORB neurons.

关键词： Orbitofrontal cortex Projection specific Rabies virus retrograde tracing Anterograde transsynaptic virus tracing Inhibitory neurons

来源：评论

学校读者我要写书评

暂无评论

InteBOMB:Integrating generic object tracking and segmentation with pose estimation for animal behavior analysis

引用

Zoological Research 2025年第2期46卷 355-369页

作者： Hao Zhai Hai-Yang Yan Jing-Yuan Zhou Jing Liu Qi-Wei Xie Li-Jun Shen Xi Chen Hua Han Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Future Technology School of Artificial IntelligenceUniversity of Chinese Academy of SciencesBeijing 101408China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong UniversityShanghai 200240China Research Base of Beijing Modern Manufacturing Development Beijing University of TechnologyBeijing 100124China

Advancements in animal behavior quantification methods have driven the development of computational ethology,enabling fully automated behavior *** multianimal pose estimation workflows rely on tracking-bydetection frameworks for either bottom-up or top-down approaches,requiring retraining to accommodate diverse animal *** study introduces InteBOMB,an integrated workflow that enhances top-down approaches by incorporating generic object tracking,eliminating the need for prior knowledge of target animals while maintaining broad *** includes two key strategies for tracking and segmentation in laboratory environments and two techniques for pose estimation in natural ***“background enhancement”strategy optimizesforeground-backgroundcontrastiveloss,generating more discriminative correlation ***“online proofreading”strategy stores human-in-the-loop long-term memory and dynamic short-term memory,enabling adaptive updates to object visual ***“automated labeling suggestion”technique reuses the visual features saved during tracking to identify representative frames for training set ***,the“joint behavior analysis”technique integrates these features with multimodal data,expanding the latent space for behavior classification and *** evaluate the framework,six datasets of mice and six datasets of nonhuman primates were compiled,covering laboratory and natural *** results demonstrated a24%improvement in zero-shot generic tracking and a 21%enhancement in joint latent space performance across datasets,highlighting the effectiveness of this approach in robust,generalizable behavior analysis.

关键词： Generic object tracking Pose estimation Behavior analysis Background subtraction Online learning Selective labeling Joint latent space

来源：评论

学校读者我要写书评

暂无评论

Temporal Knowledge Sharing Enable Spiking Neural Network Learning from Past and Future

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial intelligence 2024年第7期5卷 3524-3534页

作者： Dong, Yiting Zhao, Dongcheng Zeng, Yi University of Chinese Academy of Sciences School of Future Technology Beijing100049 China Chinese Academy of Sciences Brain-Inspired Cognitive Intelligence Lab Institute of Automation Beijing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence The School of Future Technology Beijing100049 China Chinese Academy of Sciences Key Laboratory of Brain Cognition and Brain-Inspired Intelligence Technology Shanghai200031 China

Spiking neural networks (SNNs) have attracted significant attention from researchers across various domains due to their brain-inspired information processing mechanism. However, SNNs typically grapple with challenges such as extended time steps, low temporal information utilization, and the requirement for consistent time step between testing and training. These challenges render SNNs with high latency. Moreover, the constraint on time steps necessitates the retraining of the model for new deployments, reducing adaptability. To address these issues, this article proposed a novel perspective, viewing the SNN as a temporal aggregation model. We introduced the temporal knowledge sharing (TKS) method, facilitating information interact between different time points. TKS can be perceived as a form of temporal self-distillation. To validate the efficacy of TKS in information processing, we tested it on static datasets such as CIFAR10, CIFAR100, ImageNet-1k, and neuromorphic datasets such as DVS-CIFAR10 and NCALTECH101. Experimental results demonstrated that our method achieves state-of-the-art performance compared to other algorithms. Furthermore, TKS addresses the temporal consistency challenge, endowing the model with superior temporal generalization capabilities. This allows the network to train with longer time steps and maintain high performance during testing with shorter time steps. Such an approach considerably accelerates the deployment of SNNs on edge devices. Finally, we conducted ablation experiments and tested TKS on fine-grained tasks, with results showcasing TKS's enhanced capability to process information efficiently. © 2020 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

A Circuit Domain Generalization Framework for Efficient Logic Synthesis in Chip Design 41

A Circuit Domain Generalization Framework for Efficient Logi...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Wang, Zhihai Chen, Lei Wang, Jie Bai, Yinqi Li, Xing Li, Xijun Yuan, Mingxuan Hao, Jianye Zhang, Yongdong Wu, Feng CAS Key Laboratory of Technology in GIPAS & MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition University of Science and Technology of China China Noah's Ark Lab Huawei Technologies China College of Intelligence and Computing Tianjin University China

Logic Synthesis (LS) plays a vital role in chip design. A key task in LS is to simplify circuits-modeled by directed acyclic graphs (DAGs)-with functionality-equivalent transformations. To tackle this task, many LS heuristics apply transformations to subgraphs-rooted at each node on an input DAG-sequentially. However, we found that a large number of transformations are ineffective, which makes applying these heuristics highly time-consuming. In particular, we notice that the runtime of the Resub and Mfs2 heuristics often dominates the overall runtime of LS optimization processes. To address this challenge, we propose a novel data-driven LS heuristic paradigm, namely PruneX, to reduce ineffective transformations. The major challenge of developing PruneX is to learn models that well generalize to unseen circuits, i.e., the out-of-distribution (OOD) generalization problem. Thus, the major technical contribution of PruneX is the novel circuit domain generalization framework, which learns domain-invariant representations based on the transformation-invariant domain-knowledge. To the best of our knowledge, PruneX is the first approach to tackle the OOD problem in LS heuristics. We integrate PruneX with the aforementioned Resub and Mfs2 heuristics. Experiments demonstrate that PruneX significantly improves their efficiency while keeping comparable optimization performance on industrial and very large-scale circuits, achieving up to 3.1× faster runtime. Copyright 2024 by the author(s)

关键词： Logic Synthesis

来源：评论

学校读者我要写书评

暂无评论

SpikeVoice: High-Quality Text-to-Speech Via Efficient Spiking Neural Network 62

SpikeVoice: High-Quality Text-to-Speech Via Efficient Spikin...

引用

62nd Annual Meeting of the Association for Computational Linguistics, ACL 2024

作者： Wang, Kexin Zhang, Jiahong Ren, Yong Yao, Man Shang, Di Xu, Bo Li, Guoqi Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology Beijing China

ISBN: (纸本)9798891760943

Brain-inspired Spiking Neural Network (SNN) has demonstrated its effectiveness and efficiency in vision, natural language, and speech understanding tasks, indicating their capacity to "see", "listen", and "read". In this paper, we design SpikeVoice, which performs high-quality Text-To-Speech (TTS) via SNN, to explore the potential of SNN to "speak". A major obstacle to using SNN for such generative tasks lies in the demand for models to grasp long-term dependencies. The serial nature of spiking neurons, however, leads to the invisibility of information at future spiking time steps, limiting SNN models to capture sequence dependencies solely within the same time step. We term this phenomenon "partial-time dependency". To address this issue, we introduce Spiking Temporal-Sequential Attention (STSA) in the SpikeVoice. To the best of our knowledge, SpikeVoice is the first TTS work in the SNN field. We perform experiments using four well-established datasets that cover both Chinese and English languages, encompassing scenarios with both single-speaker and multi-speaker configurations. The results demonstrate that SpikeVoice can achieve results comparable to Artificial Neural Networks (ANN) with only 10.5% energy consumption of ANN. Both our demo and code are available as supplementary material. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

A Brain-Inspired Theory of Collective Mind Model for Efficient Social Cooperation

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial intelligence 2024年第12期5卷 6280-6289页

作者： Zhao, Zhuoya Zhao, Feifei Wang, Shiwen Sun, Yinqian Zeng, Yi Brain-Inspired Cognitive Intelligence Lab Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Future Technology University of Chinese Academy of Sciences Beijing100049 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China Key Laboratory of Brain Cognition and Brain-Inspired Intelligence Technology Chinese Academy of Sciences Shanghai200031 China Center for Long-Term Artificial Intelligence Beijing100083 China

Social intelligence manifests the capability, often referred to as the theory of mind (ToM), to discern others' behavioral intentions, beliefs, and other mental states. ToM is crucial in multiagent and human-machine interaction contexts, where each participant needs to grasp the mental states of others to respond, interact, and collaborate more effectively. Recent studies show that while the ToM model can infer beliefs, intentions, and predict future observations and actions, its application in complex tasks is significantly constrained. The challenges arise when the number of agents increases, the environment becomes more complex, and interacting with the environment and predicting the mental state of each other becomes difficult and time consuming. To overcome such limits, we take inspiration from the theory of collective mind (ToCM) mechanism, predicting observations of all other agents into a unified but plural representation and discerning how our own actions affect this mental state representation. Based on this foundation, we construct an imaginative space to simulate the multiagent interaction process, thus improving the efficiency of cooperation among multiple agents in complex decision-making environments. In various cooperative tasks with different numbers of agents, the experimental results highlight the superior cooperative efficiency and performance of our approach compared to the multiagent reinforcement learning (MARL) baselines. We achieve consistent boost on SNN- and ANN-based decision networks and demonstrate that ToCM's inferences about others' mental states can be transferred to new tasks for quickly and flexible adaptation. © 2024 IEEE.

关键词： Free energy

来源：评论

学校读者我要写书评

暂无评论

Does Large Language Model Contain Task-Specific Neurons?

Does Large Language Model Contain Task-Specific Neurons?

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Song, Ran He, Shizhu Jiang, Shuting Xian, Yantuan Gao, Shengxiang Liu, Kang Yu, Zhengtao Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming China Yunnan Key Laboratory of Artificial Intelligence Kunming China The Key Laboratory of Cognition and Decision Intelligence for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Science Beijing China

ISBN: (纸本)9798891761643

Large language models (LLMs) have demonstrated remarkable capabilities in comprehensively handling various types of natural language processing (NLP) tasks. However, there are significant differences in the knowledge and abilities required for different tasks. Therefore, it is important to understand whether the same LLM processes different tasks in the same way. Are there specific neurons in a LLM for different tasks? Inspired by neuroscience, this paper pioneers the exploration of whether distinct neurons are activated when a LLM handles different tasks. Compared with current research exploring the neurons of language and knowledge, task-specific neurons present a greater challenge due to their abstractness, diversity, and complexity. To address these challenges, this paper proposes a method for task-specific neuron localization based on Causal Gradient Variation with Special Tokens (CGVST). CGVST identifies task-specific neurons by concentrating on the most significant tokens during task processing, thereby eliminating redundant tokens and minimizing interference from non-essential neurons. Compared to traditional neuron localization methods, our approach can more effectively identify task-specific neurons. We conduct experiments across eight different public tasks. Experiments involving the inhibition and amplification of identified neurons demonstrate that our method can accurately locate task-specific neurons. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

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：