检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Taubenfeld, Amir Dover, Yaniv Reichart, Roi Goldstein, Ariel The Hebrew University of Jerusalem School of Computer Science and Engineering Google Research United States The Hebrew University Business School Jerusalem Israel Federmann Center for the Study of Rationality Hebrew University Jerusalem Israel Faculty of Data and Decision Sciences Technion Department of Cognitive and Brain Sciences Hebrew University Jerusalem Israel

The emergence of Large Language Models (LLMs), has opened exciting possibilities for constructing computational simulations designed to replicate human behavior accurately. Current research suggests that LLM-based agents become increasingly human-like in their performance, sparking interest in using these AI agents as substitutes for human participants in behavioral studies. However, LLMs are complex statistical learners without straightforward deductive rules, making them prone to unexpected behaviors. Hence, it is crucial to study and pinpoint the key behavioral distinctions between humans and LLM-based agents. In this study, we highlight the limitations of LLMs in simulating human interactions, particularly focusing on LLMs’ ability to simulate political debates on topics that are important aspects of people’s day-to-day lives and decision-making processes. Our findings indicate a tendency for LLM agents to conform to the model’s inherent social biases despite being directed to debate from certain political perspectives. This tendency results in behavioral patterns that seem to deviate from well-established social dynamics among humans. We reinforce these observations using an automatic self-fine-tuning method, which enables us to manipulate the biases within the LLM and demonstrate that agents subsequently align with the altered biases. These results underscore the need for further research to develop methods that help agents overcome these biases, a critical step toward creating more realistic simulations. © 2024, CC BY.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

Robust Saliency-Aware Distillation for Few-shot Fine-grained Visual Recognition

arXiv

引用

arXiv 2023年

作者： Liu, Haiqi Chen, C.L. Philip Gong, Xinrong Zhang, Tong The School of Computer Science and Engineering South China University of Technology Guangzhou510006 China The Brain and Affective Cognitive Research Center Pazhou Lab. Guangzhou510335 China The Engineering Research Center The Ministry of Education on Health Intelligent Perception and Paralleled Digital-Human Guangzhou510006 China

Recognizing novel sub-categories with scarce samples is an essential and challenging research topic in computer vision. Existing literature addresses this challenge by employing local-based representation approaches, which may not sufficiently facilitate meaningful object-specific semantic understanding, leading to a reliance on apparent background correlations. Moreover, they primarily rely on high-dimensional local descriptors to construct complex embedding space, potentially limiting the generalization. To address the above challenges, this article proposes a novel model, Robust Saliency-aware Distillation (RSaD), for few-shot fine-grained visual recognition. RSaD introduces additional saliency-aware supervision via saliency detection to guide the model toward focusing on the intrinsic discriminative regions. Specifically, RSaD utilizes the saliency detection model to emphasize the critical regions of each sub-category, providing additional object-specific information for fine-grained prediction. RSaD transfers such information with two symmetric branches in a mutual learning paradigm. Furthermore, RSaD exploits inter-regional relationships to enhance the informativeness of the representation and subsequently summarize the highlighted details into contextual embeddings to facilitate the effective transfer, enabling quick generalization to novel sub-categories. The proposed approach is empirically evaluated on three widely used benchmarks, demonstrating its superior performance. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Enhanced Local Attention with Deep Neural Networks for EEG Decoding 4th

Enhanced Local Attention with Deep Neural Networks for EEG...

引用

4th International Workshop on Human brain and Artificial Intelligence, HBAI 2024

作者： Tao, Wei Ye, Jiawo Ieong, Chio-In Wu, Haiyan Wan, Feng Department of Electrical and Computer Engineering Faculty of Science and Technology University of Macau Taipa China Centre for Cognitive and Brain Sciences Institute of Collaborative Innovation University of Macau Taipa China Centre for Artificial Intelligence and Robotics Institute of Collaborative Innovation University of Macau Taipa China Guangdong Institute of Intelligence Science and Technology Zhuhai China Department of Psychology Faculty of Social Sciences University of Macau Taipa China

ISBN: (纸本)9789819640003

Channel-wise attention mechanisms have significantly improved deep learning-based decoding in brain-computer interfaces (BCIs). However, these methods often fail to fully utilize spatial and temporal dynamics, focusing instead on individual channel enhancements to the detriment of broader EEG signal dynamics. To address these limitations, we introduce the Enhanced Local Attention (ELA) module, seamlessly integrated into deep neural networks that enhances EEG decoding performance. It captures long-range dependencies from deep features across two dimensions through a streamlined architecture. The ELA module employs adaptive 1D convolution for precise localization of spatial and temporal information without reducing dimensions. Additionally, it utilizes group normalization to enhance feature representation by normalizing features across groups. Its lightweight design enables easy integration into existing deep learning frameworks. Comprehensive evaluations on the BCI-IV2b dataset highlight the ELA module’s superior performance. Specifically, it increases the decoding accuracy of EEGNet in the motor imagery task from 81.89% to 85.97%. Furthermore, when integrated with ADFCNN, the ELA module achieves an accuracy of 88.13%, consistently outperforming other state-of-the-art methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

DOMINO++: Domain-Aware Loss Regularization for Deep Learning Generalizability 26th

DOMINO++: Domain-Aware Loss Regularization for Deep Learning...

引用

26th International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 2023

作者： Stolte, Skylar E. Volle, Kyle Indahlastari, Aprinda Albizu, Alejandro Woods, Adam J. Brink, Kevin Hale, Matthew Fang, Ruogu Gainesville United States Torch Technologies LLC ShalimarFL United States Center for Cognitive Aging and Memory McKnight Brain Institute UF Gainesville United States Department of Clinical and Health Psychology College of Public Health and Health Professions UF Gainesville United States Department of Neuroscience College of Medicine UF Gainesville United States United States Air Force Research Laboratory Eglin Air Force Base ValparaisoFL United States Department of Electrical and Computer Engineering Herbert Wertheim College of Engineering UF Gainesville United States Department of Computer Information and Science and Engineering Herbert Wertheim College of Engineering UF Gainesville United States Department of Mechanical and Aerospace Engineering Herbert Wertheim College of Engineering UF Gainesville United States

ISBN: (纸本)9783031439001

Out-of-distribution (OOD) generalization poses a serious challenge for modern deep learning (DL). OOD data consists of test data that is significantly different from the model’s training data. DL models that perform well on in-domain test data could struggle on OOD data. Overcoming this discrepancy is essential to the reliable deployment of DL. Proper model calibration decreases the number of spurious connections that are made between model features and class outputs. Hence, calibrated DL can improve OOD generalization by only learning features that are truly indicative of the respective classes. Previous work proposed domain-aware model calibration (DOMINO) to improve DL calibration, but it lacks designs for model generalizability to OOD data. In this work, we propose DOMINO++, a dual-guidance and dynamic domain-aware loss regularization focused on OOD generalizability. DOMINO++ integrates expert-guided and data-guided knowledge in its regularization. Unlike DOMINO which imposed a fixed scaling and regularization rate, DOMINO++ designs a dynamic scaling factor and an adaptive regularization rate. Comprehensive evaluations compare DOMINO++ with DOMINO and the baseline model for head tissue segmentation from magnetic resonance images (MRIs) on OOD data. The OOD data consists of synthetic noisy and rotated datasets, as well as real data using a different MRI scanner from a separate site. DOMINO++’s superior performance demonstrates its potential to improve the trustworthy deployment of DL on real clinical data. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Magnetic resonance

来源：评论

学校读者我要写书评

暂无评论

Effect of Music Training in Neural Responses to Emotional Speech Prosody: Insights from EEG and brain Network Analysis 4th

Effect of Music Training in Neural Responses to Emotional...

引用

4th International Workshop on Human brain and Artificial Intelligence, HBAI 2024

作者： Gao, Ci-Jun Liu, Xucheng Jia, Gufeng Yang, Hongzhe Tao, Wei Wu, Haiyan Huang, Ruey-Song Wan, Feng Department of Psychology Faculty of Social Sciences University of Macau Taipa China Centre for Cognitive and Brain Sciences Institute of Collaborative Innovation University of Macau Taipa China Department of Electrical and Computer Engineering Faculty of Science and Technology University of Macau Taipa China Centre for Artificial Intelligence and Robotics Institute of Collaborative Innovation University of Macau Taipa China

ISBN: (纸本)9789819640003

Speech prosody conveys crucial information during social communication. However, the neural mechanisms underlying speech pro-sody in the human brain remain unclear. The primary aim of this study was to explore the impact of long-term musical training on the recognition of emotional speech prosody. Employing a task that isolated prosody recognition without semantic content interference, we recorded behavioral and electrophysiological data. Participants were categorized into two groups: individuals with systematic musical training and those without any formal musical training. Our findings indicate that the musician group exhibited enhanced neural activity in the frontal region, characterized by significant differences in the P50, P200, P3a, P3b, and P600 components. Additionally, a larger Power Spectral Density (PSD) was observed in the frontal, occipital, and parietal regions of musicians, particularly in the theta and alpha frequency bands. Graph theoretical analysis also indicated that musically trained individuals demonstrated an increased local coefficient and more concentrated degree. This study provides a comprehensive analysis of the neural alteration during speech prosody recognition attributable to long-term musical training, incorporating both static and dynamic analyses, with a focus on temporal and spatial dimensions. Our study provides new insights into the neural mechanisms induced by speech prosody. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Power spectral density

来源：评论

学校读者我要写书评

暂无评论

Quantum-brain: Quantum-Inspired Neural Network Approach to Vision-brain Understanding

arXiv

引用

arXiv 2024年

作者： Nguyen, Hoang-Quan Nguyen, Xuan-Bac Churchill, Hugh Choudhary, Arabinda Kumar Sinha, Pawan Khan, Samee U. Luu, Khoa Dept. of Electrical Engineering & Computer Science University of Arkansas AR United States Dept. of Physics University of Arkansas AR United States Dept. of Radiology SUNY Upstate Medical University NY United States Dept. of Brain & Cognitive Sciences Massachusetts Institute of Technology MA United States Dept. of Electrical Engineering & Computer Engineering Mississippi State University MS United States

Vision-brain understanding aims to extract semantic information about brain signals from human perceptions. Existing deep learning methods for vision-brain understanding are usually introduced in a traditional learning paradigm missing the ability to learn the connectivities between brain regions. Meanwhile, the quantum computing theory offers a new paradigm for designing deep learning models. Motivated by the connectivities in the brain signals and the entanglement properties in quantum computing, we propose a novel Quantum-brain approach, a quantum-inspired neural network, to tackle the vision-brain understanding problem. To compute the connectivity between areas in brain signals, we introduce a new Quantum-Inspired Voxel-Controlling module to learn the impact of a brain voxel on others represented in the Hilbert space. To effectively learn connectivity, a novel Phase-Shifting module is presented to calibrate the value of the brain signals. Finally, we introduce a new Measurement-like Projection module to present the connectivity information from the Hilbert space into the feature space. The proposed approach can learn to find the connectivities between fMRI voxels and enhance the semantic information obtained from human perceptions. Our experimental results on the Natural Scene Dataset benchmarks illustrate the effectiveness of the proposed method with Top-1 accuracies of 95.1% and 95.6% on image and brain retrieval tasks and an Inception score of 95.3% on fMRI-to-image reconstruction task. Our proposed quantum-inspired network brings a potential paradigm to solving the vision-brain problems via the quantum computing theory. © 2024, CC BY.

关键词： Hilbert spaces

来源：评论

学校读者我要写书评

暂无评论

Detecting Major Depression Disorder with Multiview Eye Movement Features in a Novel Oil Painting Paradigm

Detecting Major Depression Disorder with Multiview Eye Movem...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Tian-Fang Ma Lu-Yu Liu Li-Ming Zhao Dan Peng Yong Lu Wei-Long Zheng Bao-Liang Lu Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China Emotion Helper Shanghai China RuiJin-Mihoyo Laboratory Clinical Neuroscience Center RuiJin Hospital Shanghai Jiao Tong University School of Medicine Shanghai China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Major Depressive Disorder (MDD) is a debilitating condition marked by persistent low mood, reduced interest, cognitive impairments, and vegetative neurological symptoms such as sleep and appetite disturbances. In this paper, we collected eye movement signals from 40 patients diagnosed with MDD and 40 healthy controls to study the relation between eye movements and cognitive processes for depression detection. The eye movement data were captured during a novel emotional cognition task using oil paintings. Subsequently, the data were transformed into multiview eye movement features, including heatmaps, trajectories, and statistical vectors. Rigorous statistical analyses were then conducted on these features to identify significant patterns and correlations between eye movements and depressive symptoms. A multiview invariant & specific eye movement model (MISEYE) was proposed to fuse different eye movement features. The proposed achieved an accuracy rate of 79.88% in depression detection. This performance surpassed not only the outcomes of single-mode approaches and combinations of any two features but also outperformed other fusion methodologies. These findings not only shed light on the intricate relationship between eye movement patterns and MDD but also underscore the potential of eye-tracking technology in psychiatric research.

关键词： Heating systems Accuracy Statistical analysis Oils Depression Feature extraction Vectors

来源：评论

学校读者我要写书评

暂无评论

Designing Perceptual Puzzles by Differentiating Probabilistic programs 22

Designing Perceptual Puzzles by Differentiating Probabilisti...

引用

ACM SIGGRAPH 2022 Conference Proceedings

作者： Kartik Chandra Tzu-Mao Li Joshua Tenenbaum Jonathan Ragan-Kelley Computer Science & Artificial Intelligence Laboratory (CSAIL) Massachusetts Institute of Technology (MIT) United States of America Department of Computer Science and Engineering (CSE) University of California San Diego United States of America Department of Brain and Cognitive Sciences (BCS) Center for Brains Minds & Machines (CBMM) Computer Science & Artificial Intelligence Laboratory (CSAIL) Massachusetts Institute of Technology (MIT) United States of America

ISBN: (纸本)9781450393379

We design new visual illusions by finding “adversarial examples” for principled models of human perception — specifically, for probabilistic models, which treat vision as Bayesian inference. To perform this search efficiently, we design a differentiable probabilistic programming language, whose API exposes MCMC inference as a first-class differentiable function. We demonstrate our method by automatically creating illusions for three features of human vision: color constancy, size constancy, and face perception.

关键词： differentiable programming illusions probabilistic programming

来源：评论

学校读者我要写书评

暂无评论

Sex differences in autism spectrum disorder using class imbalance adjusted functional connectivity

引用

NeuroImage 2024年 304卷 120956-120956页

作者： Namgung, Jong Young Mun, Jongmin Park, Yeongjun Kim, Jaeoh Park, Bo-yong Department of Data Science Inha University Incheon South Korea Data Sciences and Operations Department Marshall School of Business University of Southern California Los Angeles United States Department of Electrical and Computer Engineering Sungkyunkwan University Suwon South Korea Department of Brain and Cognitive Engineering Korea University Seoul South Korea Center for Neuroscience Imaging Research Institute for Basic Science Suwon South Korea

Autism spectrum disorder (ASD) is an atypical neurodevelopmental condition with a diagnostic ratio largely differing between male and female participants. Due to the sex imbalance in participants with ASD, we lack an understanding of the differences in connectome organization of the brain between male and female participants with ASD. In this study, we matched the sex ratio using a Gaussian mixture model-based oversampling technique and investigated the differences in functional connectivity between male and female participants with ASD using low-dimensional principal gradients. Between-group comparisons of the gradient values revealed significant interaction effects of sex in the sensorimotor, attention, and default mode networks. The sex-related differences in the gradients were highly associated with higher-order cognitive control processes. Transcriptomic association analysis provided potential biological underpinnings, specifying gene enrichment in the cortex, thalamus, and striatum during development. Finally, the principal gradients were differentially associated with symptom severity of ASD between sexes, highlighting significant effects in female participants with ASD. Our work proposed an oversampling method to mitigate sex imbalance in ASD and observed significant sex-related differences in functional connectome organization. The findings may advance our knowledge about the sex heterogeneity in large-scale brain networks in ASD. © 2024 The Author(s)

关键词： Autism spectrum disorder Class imbalance Functional gradient Gaussian mixture model Oversampling Sex difference

来源：评论

学校读者我要写书评

暂无评论

ON THE WEAKNESSES OF REINFORCEMENT LEARNING FOR NEURAL MACHINE TRANSLATION 8

ON THE WEAKNESSES OF REINFORCEMENT LEARNING FOR NEURAL MACHI...

引用

8th International Conference on Learning Representations, ICLR 2020

作者： Choshen, Leshem Fox, Lior Aizenbud, Zohar Abend, Omri School of Computer Science and Engineering The Edmond and Lily Safra Center for Brain Sciences Israel Department of Cognitive Sciences The Hebrew University of Jerusalem Israel

Reinforcement learning (RL) is frequently used to increase performance in text generation tasks, including machine translation (MT), notably through the use of Minimum Risk Training (MRT) and Generative Adversarial Networks (GAN). However, little is known about what and how these methods learn in the context of MT. We prove that one of the most common RL methods for MT does not optimize the expected reward, as well as show that other methods take an infeasibly long time to converge. In fact, our results suggest that RL practices in MT are likely to improve performance only where the pre-trained parameters are already close to yielding the correct translation. Our findings further suggest that observed gains may be due to effects unrelated to the training signal, concretely, changes in the shape of the distribution curve. © 2020 8th International Conference on Learning Representations, ICLR 2020. 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

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：