检索结果-内蒙古大学图书馆

An Overview and Perspectives On Bidirectional Intelligence: Lmser Duality, Double IA Harmony,and Causal Computation

IEEE/CAA Journal of Automatica Sinica 2019年第4期6卷 865-893页

作者： Lei Xu IEEE the Center for Cognitive Madmnes and Computational Health(CMaCH) School of Electronic Information and Electrical EngineeringShanghai Jiao Tong University Neural Computation Research Centre in Brain and Intelligence Science-Technology Institute Shanghai ZhangJiang National Lab

Advances on bidirectional intelligence are overviewed along three threads,with extensions and new *** first thread is about bidirectional learning architecture,exploring five dualities that enable Lmser six cognitive functions and provide new perspectives on which a lot of extensions and particularlly flexible Lmser are ***,either or two of these dualities actually takes an important role in recent models such as U-net,ResNet,and Dense *** second thread is about bidirectional learning principles unified by best yIng-yAng(IA)harmony in BYY *** getting insights on deep bidirectional learning from a bird-viewing on existing typical learning principles from one or both of the inward and outward directions,maximum likelihood,variational principle,and several other learning principles are summarised as exemplars of the BYY learning,with new perspectives on advanced *** third thread further proceeds to deep bidirectional intelligence,driven by long term dynamics(LTD)for parameter learning and short term dynamics(STD)for image thinking and rational thinking in *** thinking deals with information flow of continuously valued arrays and especially image sequence,as if thinking was displayed in the real world,exemplified by the flow from inward encoding/cognition to outward reconstruction/transformation performed in Lmser learning and BYY *** contrast,rational thinking handles symbolic strings or discretely valued vectors,performing uncertainty reasoning and problem *** particular,a general thesis is proposed for bidirectional intelligence,featured by BYY intelligence potential theory(BYY-IPT)and nine essential dualities in architecture,fundamentals,and implementation,***,problems of combinatorial solving and uncertainty reasoning are investigated from this BYY IPT ***,variants and extensions are suggested for AlphaGoZero like searching tasks,such as traveling salesman probl

关键词： Autoencoder LMSER duality outward attention associative recall concept formation imagining pattern transformation STD vs LTD RPCL skip connection feedback variational least redundancy Bayesian Ying Yang IA system best harmony best matching image thinking rational thinking intelligence potential theory Alpha-TSP Alpha-AGM graph matching ME Player BYY Follower constraint satisfaction causal potential theory

来源：评论

学校读者我要写书评

暂无评论

Detecting Brain State Changes via Manifold Mean Shifting

Detecting Brain State Changes via Manifold Mean Shifting

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Zhuobin Huang Tingting Dan Yi Lin Jiazhou Chen Hongmin Cai Guorong Wu School of Computer Science and Engineering South China University of Technology Guangzhou China Brain and Affective Cognitive Research Center Pazhou Lab Guangzhou China University of North Carolina at Chapel Hill Chapel Hill NC USA

ISBN: (纸本)9781665429825

The topology of human functional networks is assumed to oscillate during brain states changes. The functional neuroimage is employed to offer a non-invasive window to understand cognition and behaviors by characterizing the functional connections between spatially distinct brain regions. Consequently, identifying the transitions of functional connectivities is the critical step to understanding the mechanism of cognition that might be underlined with neurological disorders. However, little attention has been paid to studying the geometry of the entire functional brain network. To tackle this issue, this paper models the cognition changes on functional brain networks as a set of landmarks residing on a Riemannian manifold. Accordingly, we propose a Riemannian manifold mean shift method to detect cognition changes by identifying the representative function networks of the distribution of functional networks. The manifold mean shift (MMS) method is applied on both simulated data and real functional neuroimaging data, downloaded from Human Connectome Project (HCP). Experimental results demonstrated the MMS achieved highly accurate and consistent cognition change, by comparing three state-of-the-art methods.

关键词： Manifolds Geometry Neurological diseases Network topology Conferences Network analyzers Functional neuroimaging

来源：评论

学校读者我要写书评

暂无评论

Neural population geometry reveals the role of stochasticity in robust perception

arXiv

引用

arXiv 2021年

作者： Dapello, Joel Feather, Jenelle Le, Hang Marques, Tiago Cox, David D. McDermott, Josh H. DiCarlo, James J. Chung, SueYeon Department of Brain and Cognitive Sciences Massachusetts Institute of Technology McGovern Institute for Brain Research Massachusetts Institute of Technology School of Engineering and Applied Sciences Harvard University Center for Brains Minds and Machines Massachusetts Institute of Technology MIT-IBM Watson AI Lab Speech and Hearing Bioscience and Technology Harvard University Center for Theoretical Neuroscience Columbia University Zuckerman Institute Columbia Univeristy

Adversarial examples are often cited by neuroscientists and machine learning researchers as an example of how computational models diverge from biological sensory systems. Recent work has proposed adding biologically-inspired components to visual neural networks as a way to improve their adversarial robustness. One surprisingly effective component for reducing adversarial vulnerability is response stochasticity, like that exhibited by biological neurons. Here, using recently developed geometrical techniques from computational neuroscience, we investigate how adversarial perturbations influence the internal representations of standard, adversarially trained, and biologically-inspired stochastic networks. We find distinct geometric signatures for each type of network, revealing different mechanisms for achieving robust representations. Next, we generalize these results to the auditory domain, showing that neural stochasticity also makes auditory models more robust to adversarial perturbations. Geometric analysis of the stochastic networks reveals overlap between representations of clean and adversarially perturbed stimuli, and quantitatively demonstrates that competing geometric effects of stochasticity mediate a tradeoff between adversarial and clean performance. Our results shed light on the strategies of robust perception utilized by adversarially trained and stochastic networks, and help explain how stochasticity may be beneficial to machine and biological computation. Copyright © 2021, The Authors. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Periodic DMP formulation for quaternion trajectories

arXiv

引用

arXiv 2021年

作者： Abu-Dakka, Fares J. Saveriano, Matteo Peternel, Luka Intelligent Robotics Group Dept of Electrical Engineering and Automation Aalto University Finland Dept of Computer Science and Digital Science Center University of Innsbruck Austria Delft Haptics Lab Dept of Cognitive Robotics Delft University of Technology Delft Netherlands

Imitation learning techniques have been used as a way to transfer skills to robots. Among them, dynamic movement primitives (DMPs) have been widely exploited as an effective and an efficient technique to learn and reproduce complex discrete and periodic skills. While DMPs have been properly formulated for learning point-to-point movements for both translation and orientation, periodic ones are missing a formulation to learn the orientation. To address this gap, we propose a novel DMP formulation that enables encoding of periodic orientation trajectories. Within this formulation we develop two approaches: Riemannian metric-based projection approach and unit quaternion based periodic DMP. Both formulations exploit unit quaternions to represent the orientation. However, the first exploits the properties of Riemannian manifolds to work in the tangent space of the unit sphere. The second encodes directly the unit quaternion trajectory while guaranteeing the unitary norm of the generated quaternions. We validated the technical aspects of the proposed methods in simulation. Then we performed experiments on a real robot to execute daily tasks that involve periodic orientation changes (i.e., surface polishing/wiping and liquid mixing by shaking). © 2021, CC BY.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Detection-and-Excitation Neural Network Achieves Accurate Nasopharyngeal Carcinoma Segmentation in Multi-modality MR Images

Detection-and-Excitation Neural Network Achieves Accurate Na...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Guihua Tao Haojiang Li Lizhi Liu Hongmin Cai School of Computer Science and Engineering South China University of Technology Guangzhou China Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy Collaborative Innovation Center for Cancer Medicine Sun Yat-sen University Cancer Center Guangzhou China Brain and Affective Cognitive Research Center Pazhou Lab Guangzhou China

ISBN: (纸本)9781665429825

Accurate and reliable segmentation of nasopharyngeal carcinoma (NPC) in magnetic resonance image (MRI) is important for treatment planning and follow-up evaluation. However, it is still challenging because NPC is infiltrative with a vague border and has a tiny volume with varying sizes and shapes. The above problems easily cause the NPC tumors’ features to submerge in the process of feature extraction. Standard segmentation methods do not cope with the “feature submergence” and performed unsatisfactorily in NPC segmentation. To address the problem, a dual-supervised method equipped with the detection-and-excitation module (DEM) was proposed. DEM strengthens the region of interest (ROI) and weakens complex and immense background through incorporating detection feature maps (outline maps) with intermediated segmentation features. To be specific, the DEM explored the outline of the ROI and output a detection feature map by using a supervised layer guided by a tailored loss function. Then, the DEM uses the results to recalibrates the intermediated segmentation. Finally, a neural network equipped with the proposed DEM was elaborately designed to achieve accurate segmentation. We applied the proposed network termed as DENet on a real nasopharyngeal carcinoma dataset to realize automatic NPC tumors segmentation in multi-modality MR images. The proposed DEM enables the neural network to segment NPC tumors within the immense and complex background. Experimental results have demonstrated the effectiveness of the proposed method by comparing it with benchmark models.

关键词： Image segmentation Shape Neural networks Semantics Feature extraction Planning Reliability

来源：评论

学校读者我要写书评

暂无评论

AM-ConvBLS: Adaptive Manifold Convolutional Broad Learning System for Cross-Session and Cross-Subject Emotion Recognition

引用

IEEE Transactions on Affective Computing 2025年

作者： Lei, Chunyu Chen, C. L. Philip Zhang, Tong South China University of Technology Guangdong Provincial Key Laboratory of Computational Intelligence and Cyberspace Information The School of Computer Science and Engineering Guangzhou510006 China Pazhou Lab Brain and Affective Cognitive Research Center Guangzhou510335 China Ministry of Education on Health Intelligent Perception and Paralleled Digital-Human Engineering Research Center Guangzhou China

Emotion recognition based on electroencephalography (EEG) data has gained rapid development because of its believability and accuracy. However, most existing EEG emotion recognition methods suffer from three issues: 1) underutilization of multi-scale emotion representations, 2) underexploitation of emotion labels and intrinsic geometric structures, and 3) inherent non-stationarity characteristic and individual variability of EEG signals. To this end, we propose an Adaptive Manifold Convolutional Broad Learning System (AM-ConvBLS) to capture the multi-scale distribution aligned emotion patterns in the geometric structure preserved emotion submanifold space. To begin with, a Multi-Scale Representation Learning (MSRL) module is developed to learn diverse multi-scale emotion representations. The Domain Discrepancy Elimination (DDE) module is then developed to further align feature distributions in the source and target domains. To further utilize EEG emotion labels, we devise a label Manifold Information Exploration (LMIE) module to retain the sample label consistency. In addition, a global feature importance analysis method for AM-ConvBLS based on Shapley Additive Global importancE (SAGE) is designed to investigate the EEG frequency band importance and brain neural activation patterns. Experiments on SEED, SEED-IV, and SEED-V datasets demonstrate the effectiveness and superiority of our AM-ConvBLS. © 2010-2012 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

SUMMARY ON THE ICASSP 2022 MULTI-CHANNEL MULTI-PARTY MEETING TRANSCRIPTION GRAND CHALLENGE

arXiv

引用

arXiv 2022年

作者： Yu, Fan Zhang, Shiliang Guo, Pengcheng Fu, Yihui Du, Zhihao Zheng, Siqi Huang, Weilong Xie, Lei Tan, Zheng-Hua Wang, DeLiang Qian, Yanmin Lee, Kong Aik Yan, Zhijie Ma, Bin Xu, Xin Bu, Hui Speech Lab Alibaba Group China Speech Lab Alibaba Group Singapore AISHELL Foundation China Beijing Shell Shell Technology Co. Ltd. Beijing China Department of Electronic Systems Aalborg University Aalborg Denmark Department of Computer Science and Engineering Center for Cognitive and Brain Sciences The Ohio State University United States SpeechLab Department of Computer Science and Engineering Shanghai Jiao Tong University China Aural and Language Intelligence Department Institute for Infocomm Research A*STAR Singapore

The ICASSP 2022 Multi-channel Multi-party Meeting Transcription Grand Challenge (M2MeT) focuses on one of the most valuable and the most challenging scenarios of speech technologies. The M2MeT challenge has particularly set up two tracks, speaker diarization (track 1) and multi-speaker automatic speech recognition (ASR) (track 2). Along with the challenge, we released 120 hours of real-recorded Mandarin meeting speech data with manual annotation, including far-field data collected by 8-channel microphone array as well as near-field data collected by each participants’ headset microphone. We briefly describe the released dataset, track setups, baselines and summarize the challenge results and major techniques used in the submissions. © 2022, CC BY-SA.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Automated Detection of Epileptic Spikes and Seizures Incorporating a Novel Spatial Clustering Prior

arXiv

引用

arXiv 2025年

作者： Dong, Hanyang Sheng, Shurong Wang, Xiongfei Gao, Jia-Hong Sun, Yi Yang, Wanli Xiao, Kuntao Teng, Pengfei Luan, Guoming Lv, Zhao School of Artificial Intelligence Anhui University Hefei230601 China Anhui Province Key Laboratory of Biomedical Imaging and Intelligent Processing Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230088 China Department of Neurosurgery Beijing Key Laboratory of Epilepsy Sanbo Brain Hospital Capital Medical University Beijing China McGovern Institute for Brain Research Peking University Beijing China Center for MRI Research Academy for Advanced Interdisciplinary Studies Peking University Beijing China Beijing City Key Lab for Medical Physics and Engineering Institute of Heavy Ion Physics School of Physics Peking University Beijing China Anhui Province Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China

A Magnetoencephalography (MEG) time-series recording consists of multi-channel signals collected by superconducting sensors, with each signal’s intensity reflecting magnetic field changes over time at the sensor location. Automating epileptic MEG spike detection significantly reduces manual assessment time and effort, yielding substantial clinical benefits. Existing research addresses MEG spike detection by encoding neural network inputs with signals from all channel within a time segment, followed by classification. However, these methods overlook simultaneous spiking occurred from nearby sensors. We introduce a simple yet effective paradigm that first clusters MEG channels based on their sensor’s spatial position. Next, a novel convolutional input module is designed to integrate the spatial clustering and temporal changes of the signals. This module is fed into a custom MEEG-ResNet3D developed by the authors, which learns to extract relevant features and classify the input as a spike clip or not. Our method achieves an F1 score of 94.73% on a large real-world MEG dataset Sanbo-CMR collected from two centers, outperforming state-of-the-art approaches by 1.85%. Moreover, it demonstrates efficacy and stability in the Electroencephalographic (EEG) seizure detection task, yielding an improved weighted F1 score of 1.4% compared to current state-of-the-art techniques evaluated on TUSZ, whch is the largest EEG seizure dataset. Copyright © 2025, The Authors. All rights reserved.

关键词： Magnetoencephalography

来源：评论

学校读者我要写书评

暂无评论

Functional classification of neurons in mouse hippocampus based on spike waveforms in extracellular recordings

Functional classification of neurons in mouse hippocampus ba...

引用

Iranian Conference on Electrical engineering (ICEE)

作者： Mehrdad Oghazian Ali Khadem Moein Esghaei Faculty of Electrical Engineering K. N. Toosi University of Technology Tehran Iran Cognitive Neuroscience Lab German Primate Center Goettingen Germany

ISBN: (数字)9781728172965

ISBN: (纸本)9781728172972

Neurons are functionally classified into inhibitory and excitatory categories based on the influence they have on the firing rates of their postsynaptic neurons after being stimulated. Although assessing the firing rates of postsynaptic neurons is the main way of this categorization, it is very hard in real cases. Due to the lack of a labelled dataset with inhibitory and excitatory neurons, past studies have been conducted to investigate the feasibility of this categorization based on clustering some features of the spike waveforms and evaluating the results by physiological evidence. However, there is still the lack of a classification study in order to do this categorization by using features of spike waveforms and different classifiers. This is what we addressed in this paper based on a recent labeled dataset of mouse hippocampus neurons. We extracted nine different features from neuron spikes. Then we investigated the significance of difference of each feature between inhibitory and excitatory groups using Wilcoxon rank-sum-test and also evaluated the effectiveness of all possible feature subsets for classification using KNN, LDA, and SVM classifiers. The highest average classification accuracy was %96.96 obtained by using SVM with RBF kernel and five features. However, KNN yielded %96.08 average accuracy by using just one feature which was Peak amplitude asymmetry. In addition, Peak amplitude asymmetry, Peak-to-trough ratio, and Duration between peaks selected more in the optimum feature subsets using different classifiers. Generally, we concluded the features obtained from waveform spikes and simple common classifiers can effectively classify neurons into inhibitory and excitatory categories.

关键词： Neurons Feature extraction Support vector machines Firing Mice Statistics Sociology

来源：评论

学校读者我要写书评

暂无评论

Automated Detection of Epileptic Spikes and Seizures Incorporating a Novel Spatial Clustering Prior

Automated Detection of Epileptic Spikes and Seizures Incorpo...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Hanyang Dong Shurong Sheng Xiongfei Wang Jia-Hong Gao Yi Sun Wanli Yang Kuntao Xiao Pengfei Teng Guoming Luan Zhao Lv School of Artificial Intelligence Anhui University Hefei China Anhui Province Key Laboratory of Biomedical Imaging and Intelligent Processing Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China Department of Neurosurgery Beijing Key Laboratory of Epilepsy Sanbo Brain Hospital Capital Medical University Beijing China McGovern Institute for Brain Research Peking University Beijing China Center for MRI Research Academy for Advanced Interdisciplinary Studies Peking University Beijing China Beijing City Key Lab for Medical Physics and Engineering Institute of Heavy Ion Physics School of Physics Peking University Beijing China Anhui Province Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

关键词： Convolution Magnetic sensors Neural networks Magnetoencephalography Manuals Feature extraction Electroencephalography Encoding Recording Magnetic fields

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：