检索结果-内蒙古大学图书馆

A Novel Heterogeneous Actor-critic Algorithm with Recent Emphasizing Replay Memory

International Journal of automation and computing 2021年第4期18卷 619-631页

作者： Bao Xi Rui Wang Ying-Hao Cai Tao Lu Shuo Wang State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of SciencesShanghai 200031China

Reinforcement learning(RL) algorithms have been demonstrated to solve a variety of continuous control tasks. However,the training efficiency and performance of such methods limit further applications. In this paper, we propose an off-policy heterogeneous actor-critic(HAC) algorithm, which contains soft Q-function and ordinary Q-function. The soft Q-function encourages the exploration of a Gaussian policy, and the ordinary Q-function optimizes the mean of the Gaussian policy to improve the training efficiency. Experience replay memory is another vital component of off-policy RL methods. We propose a new sampling technique that emphasizes recently experienced transitions to boost the policy training. Besides, we integrate HAC with hindsight experience replay(HER) to deal with sparse reward tasks, which are common in the robotic manipulation domain. Finally, we evaluate our methods on a series of continuous control benchmark tasks and robotic manipulation tasks. The experimental results show that our method outperforms prior state-of-the-art methods in terms of training efficiency and performance, which validates the effectiveness of our method.

关键词： Reinforcement learning(RL) actor-critic experience replay training efficiency manipulation skill learning

来源：评论

学校读者我要写书评

暂无评论

Symptom Dimensions and Cognitive Impairments in Individuals at Clinical High Risk for Psychosis

引用

Biological Psychiatry: Cognitive Neuroscience and Neuroimaging 2025年第6期10卷 646-655页

作者： Zhang, TianHong Xu, LiHua Wei, YanYan Cui, HuiRu Tang, XiaoChen Hu, YeGang Liu, HaiChun Wang, ZiXuan Chen, Tao Yi, ZhengHui Li, ChunBo Wang, JiJun Shanghai Mental Health Center Shanghai Jiaotong University School of Medicine Shanghai Engineering Research Center of Intelligent Psychological Evaluation and Intervention Shanghai Key Laboratory of Psychotic Disorders Shanghai China Department of Automation Shanghai Jiao Tong University Shanghai China Department of Psychology Shanghai Xinlianxin Psychological Counseling Center Shanghai China Big Data Research Laboratory University of Waterloo Waterloo ON Canada Labor and Worklife Program Harvard University Cambridge Massachusetts United States Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai China Institute of Psychology and Behavioral Science Shanghai Jiao Tong University Shanghai China

Background: Understanding the intricate relationships between symptom dimensions, clusters, and cognitive impairments is crucial for early detection and intervention in individuals at clinical high risk for psychosis. This study delves into this complex interplay in a clinical high risk sample with the aim of predicting the conversion to psychosis. Methods: A comprehensive cognitive assessment was performed in 744 clinical high risk individuals. The study included a 3-year follow-up period to allow assessment of conversion to psychosis. Symptom profiles were determined using the Structured Interview for Prodromal Syndromes. By applying factor analysis, symptom dimensions were categorized as dominant negative symptoms (NS), positive symptoms-stressful, and positive symptoms-odd. The factor scores were used to define 3 dominant symptom groups. Latent class analysis (LCA) and the factor mixture model (FMM) were employed to identify discrete clusters based on symptom patterns. The 3-class solution was chosen for the LCA and FMM analysis. Results: Individuals in the dominant NS group exhibited significantly higher conversion rates to psychosis than those in the other groups. Specific cognitive variables, including performance on the Brief Visuospatial Memory Test–Revised (odds ratio = 0.702, p = .001) and Neuropsychological Assessment Battery Mazes Test (odds ratio = 0.776, p = .024), significantly predicted conversion to psychosis. Notably, cognitive impairments associated with NS and positive symptoms-stressful groups affected different cognitive domains. LCA and FMM cluster 1, which was characterized by severe NS and positive symptoms-odd, exhibited more impairments in cognitive domains than other clusters. No significant difference in the conversion rate was observed among the LCA and FMM clusters. Conclusions: These findings highlight the importance of NS in the development of psychosis and suggest specific cognitive domains that are affected by symptom dimensions.

关键词： Negative symptoms Neurocognition Subtype Transition Ultra high risk

来源：评论

学校读者我要写书评

暂无评论

Bio-inspired micro/nanostructures for flexible and stretchable electronics

引用

Nano Research 2020年第5期13卷 1244-1252页

作者： Hongbian Li Suye Lv Ying Fang CAS Key Laboratory for Biomedical Effects of Nanomaterials and Nanosafety CAS Center for Excellence in NanoscienceNational Center for Nanoscience and TechnologyBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China CAS Center for Excellence in Brain Science and Intelligence Technology Institute of NeuroscienceChinese Academy of SciencesShanghai 200031China

The remarkable ability of biological systems to sense and adapt to complex environmental conditions has inspired the design of next-generation electronics with advanced *** review focuses on emerging bio-inspired strategies for the development of flexible and stretchable electronics that can accommodate mechanical deformations and integrate seamlessly with biological *** will provide an overview of the practical considerations in the materials and structure designs of flexible and stretchable *** progress in bio-inspired pressure/strain sensors,stretchable electrodes,mesh electronics,and flexible energy devices are then discussed,with an emphasis on their unconventional micro/nanostructure designs and advanced ***,current challenges and future perspectives are identified and discussed.

关键词： bio-inspired structures mechanical sensors stretchable electrodes mesh electronics flexible energy devices

来源：评论

学校读者我要写书评

暂无评论

Overexpression of MECP2 in the Suprachiasmatic Nucleus Alters Circadian Rhythm and Induces Abnormal Social Behaviors

引用

Neuroscience Bulletin 2021年第12期37卷 1713-1717页

作者： Hailin Liu Zilong Qiu Center for Excellence in Brain Science and Intelligence Technology Institute of NeuroscienceState Key Laboratory of NeuroscienceCAS Key Laboratory of Primate NeurobiologyChinese Academy of SciencesShanghai 200031China University of Chinese Academy of Sciences Beijing 100049China Shanghai Center for Brain Science and Brain-Inspired Intelligence Technology Shanghai 201210China National Clinical Research Center for Aging and Medicine Huashan HospitalFudan UniversityShanghai 200040China

Dear Editors,Autism spectrum disorder is a highly heritable neurodevel-opmental disorder and is often associated with sleep disorders and dysregulation of the circadian rhythm[1,2].Whether neural circuits governing the circadian rhythm are causally associated with social behaviors remains to be *** this work,we used mice with MECP2 duplication as a model of autism to investigate whether regulation of the circadian rhythm is connected to social behaviors.

关键词： MECP2 rhythm connected

来源：评论

学校读者我要写书评

暂无评论

A single nonsynonymous mutation on ZIKV E protein-coding sequences leads to markedly increased neurovirulence in vivo

引用

Virologica Sinica 2022年第1期37卷 115-126页

作者： Zhihua Liu Yawei Zhang Mengli Cheng Ningning Ge Jiayi Shu Zhiheng Xu Xiao Su Zhihua Kou Yigang Tong Chengfeng Qin Xia Jin Institut Pasteur of Shanghai Chinese Academy of SciencesShanghai200031China University of Chinese Academy of Sciences Beijing100049China Vaccine and Immunology Research Center Translational Medical Research InstituteShanghai Public Health Clinical CenterFudan UniversityShanghai201508China State Key Laboratory of Pathogen and Biosecurity Beijing Institute of Microbiology and EpidemiologyBeijing100071China State Key Laboratory of Molecular Developmental Biology CAS Center for Excellence in Brain Science and Intelligence TechnologyInstitute of Genetics and Developmental BiologyChinese Academy of SciencesBeijing100101China College of Life Science and Technology Beijing University of Chemical TechnologyBeijing100029China

Zika virus(ZIKV)can infect a wide range of tissues including the developmental brain of human *** specific viral genetic variants are linked to neuropathology is incompletely *** address this,we have intracranially serially passaged a clinical ZIKV isolate(SW01)in neonatal mice and discovered variants that exhibit markedly increased virulence and *** sequencing analysis combining with molecular virology studies revealed that a single 67D(Aspartic acid)to N(Asparagine)substitution on E protein is sufficient to confer the increased virulence and neurotropism in ***,virus clones with D67N mutation had higher viral production and caused more severe cytopathic effect(CPE)in human neural astrocytes U251 cells in vitro,indicating its potential neurological toxicity to human *** findings revealed that a single mutation D67N on ZIKV envelope may lead to severe neuro lesion that may help to explain the neurovirulence of ZIKV and suggest monitoring the occurrence of this mutation during nature infection may be important.

关键词： Zika virus(ZIKV) Envelope protein D67N Mutation Neurovirulence

来源：评论

学校读者我要写书评

暂无评论

DSIC: DYNAMIC SAMPLE-INDIVIDUALIZED CONNECTOR FOR MULTI-SCALE OBJECT DETECTION

DSIC: DYNAMIC SAMPLE-INDIVIDUALIZED CONNECTOR FOR MULTI-SCAL...

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Li, Zekun Liu, Yufan Li, Bing Hu, Weiming Miao, Yanan Zhang, Hong National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China PeopleAI Inc CAS Center for Excellence in Brain Science and Intelligence Technology China CNCERT/CC China

ISBN: (纸本)9781665438643

Although object detection has reached a milestone recently, the scale variation is still the key challenge. Integrating multilevel features is presented to alleviate the problems, like Feature Pyramid Network (FPN) and its improvements. However, the specifically designed architectures and fixed data flow paths of these methods are not flexible for feature fusion, especially when fed with various samples. To overcome the limitations, we propose a Dynamic Sample-Individualized Connector (DSIC) for multi-scale object detection, which dynamically adjusts network connections to fit different samples. In particular, DSIC consists of two components: Intra-scale Selection Gate (ISG) and Cross-scale Selection Gate (CSG). With the help of the presented gate operator, ISG adaptively extracts proper multi-level features from backbone as the inputs of feature integration. CSG automatically activates informative data flow paths based on the extracted multi-level features. These two components are both plug-and-play and can be embedded in any backbone. Experimental results demonstrate that the proposed method outperforms the state-of-the-arts. © 2021 IEEE

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Online Audio-Visual Speech Separation with Generative Adversarial Training 2021

Online Audio-Visual Speech Separation with Generative Advers...

引用

7th International Conference on Computing and Artificial intelligence, ICCAI 2021

作者： Zhang, Peng Xu, Jiaming Hao, Yunzhe Xu, Bo Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Science China Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Science China Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Science Center for Excellence in Brain Science and Intelligence Technology China

ISBN: (纸本)9781450389501

Audio-visual speech separation has been demonstrated to be effective in solving the cocktail party problem. However, most of the models cannot meet online processing, which limits their application in video communication and human-robot interaction. Besides, SI-SNR, the most popular training loss function in speech separation, results in some artifacts in the separated audio, which would harm downstream applications, such as automatic speech recognition (ASR). In this paper, we propose an online audio-visual speech separation model with generative adversarial training to solve the two problems mentioned above. We build our generator (i.e., audio-visual speech separator) with causal temporal convolutional network block and propose a streaming inference strategy, which allows our model to do speech separation in an online manner. The discriminator is involved in optimizing the generator, which can reduce the negative effects of SI-SNR. Experiments on simulated 2-speaker mixtures based on challenging audio-visual dataset LRS2 show that our model outperforms the state-of-the-art audio-only model Conv-TasNet and audio-visual model advr-AVSS under the same model size. We test the running time of our model on GPU and CPU, and results show that our model meets online processing. The demo and code can be found at https://***/aispeech-lab/oavss. © 2021 ACM.

关键词： Separation

来源：评论

学校读者我要写书评

暂无评论

Exploiting High Performance Spiking Neural Networks with Efficient Spiking Patterns

arXiv

引用

arXiv 2023年

作者： Shen, Guobin Zhao, Dongcheng Zeng, Yi Brain-inspired Cognitive Intelligence Lab CASIA China Center for Excellence in Brain Science and Intelligence Technology CAS China School of Future Technology University of Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China

Spiking Neural Networks (SNNs) use discrete spike sequences to transmit information, which significantly mimics the information transmission of the brain. Although this binarized form of representation dramatically enhances the energy efficiency and robustness of SNNs, it also leaves a large gap between the performance of SNNs and Artificial Neural Networks based on real values. There are many different spike patterns in the brain, and the dynamic synergy of these spike patterns greatly enriches the representation capability. Inspired by spike patterns in biological neurons, this paper introduces the dynamic Burst pattern and designs the Leaky Integrate and Fire or Burst (LIFB) neuron that can make a trade-off between short-time performance and dynamic temporal performance from the perspective of network information capacity. LIFB neuron exhibits three modes, resting, Regular spike, and Burst spike. The burst density of the neuron can be adaptively adjusted, which significantly enriches the characterization capability. We also propose a decoupling method that can losslessly decouple LIFB neurons into equivalent LIF neurons, which demonstrates that LIFB neurons can be efficiently implemented on neuromorphic hardware. We conducted experiments on the static datasets CIFAR10, CIFAR100, and ImageNet, which showed that we greatly improved the performance of the SNNs while significantly reducing the network latency. We also conducted experiments on neuromorphic datasets DVS-CIFAR10 and NCALTECH101 and showed that we achieved state-of-the-art with a small network structure. Copyright © 2023, The Authors. All rights reserved.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

NMDA receptors: from atomic structures to diverse physiological functions

NMDA receptors: from atomic structures to diverse physiologi...

引用

2022生物物理大会

作者： Shujia Zhu Institute of Neuroscience State Key Laboratory of Neuroscience CAS Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences

N-methyl-D-aspartate (NMDA) receptors are glutamate-gated and calcium-permeable ion channels that play critical roles in neuronal development and brain *** of NMDA receptors has been implicated in a series of neuropsychiatric diseases, including depression, epilepsy, chronic pain, Alzheimer’s disease and autoimmune encephalitis. Functional NMDA receptors are typically assembled as di-heteromeric or tri-heteromeric tetramers with two obligatory GluN1 subunits and two identical or different GluN2 (2A-2D) and GluN3 (3A and 3B) subunits.

关键词： NMDA receptors from atomic structures to diverse physiological functions

来源：评论

学校读者我要写书评

暂无评论

Single-dose AAV-based vaccine induces a high level of neutralizing antibodies against SARS-CoV-2 in rhesus macaques

引用

Protein & Cell 2023年第1期14卷 69-73页

作者： Dali Tong Mei Zhang Yunru Yang Han Xia Haiyang Tong Huajun Zhang Weihong Zeng Muziying Liu Yan Wu Huan Ma Xue Hu Weiyong Liu Yuan Cai Yanfeng Yao Yichuan Yao Kunpeng Liu Shifang Shan Yajuan Li Ge Gao Weiwei Guo Yun Peng Shaohong Chen Juhong Rao Jiaxuan Zhao Juan Min Qingjun Zhu Yanmin Zheng Lianxin Liu Chao Shan Kai Zhong Zilong Qiu Tengchuan Jin Sandra Chiu Zhiming Yuan Tian Xue First Affiliated Hospital of USTC School of Life SciencesDivision of Life Sciences and MedicineUniversity of Science and Technology of ChinaHefei 230026China Hefei National Research Center for Physical Sciences at the Microscale Neurodegenerative Disorder Research CenterCAS Key Laboratory of Brain Function and DiseaseCAS Key Laboratory of Innate Immunity and Chronic DiseaseBiomedical Sciences and Health Laboratory of Anhui ProvinceUniversity of Science and Technology of ChinaHefei 230026China State Key Laboratory of Virology Wuhan Institute of VirologyChinese Academy of SciencesWuhan 430071China Center for Biosafety Mega-Science Wuhan Institute of VirologyChinese Academy of SciencesWuhan 430071China Hefei Institutes of Physical Science Chinese Academy of SciencesHefei 230031China Anhui Institute of Pediatric Research Anhui Provincial Children's HospitalHefei 230051China Chinese Academy of Sciences Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of SciencesShanghai 200031China Department of Clinical Laboratory First Affiliated Hospital of Anhui Medical UniversityHefei230022China Institute for Stem Cell and Regeneration Chinese Academy of SciencesBeijing 100101China

Dear Editor,Coronavirus disease 2019(COVID-19)is a highly infectious respiratory disease that continues to pose a serious global public health *** disease shows a high infection rate,long incubation period,and rapidly emerging variants,which have led to its rapid spread worldwide(Krammer 2020).Many vaccines have been developed for the control of severe acute respiratory syndrome coronavirus 2(SARS-CoV-2),the virus responsible for COVID-19,including vaccines based on messenger RNA(mRNA)(Polack et al.2020),viral vectors(Zhu et al.2020),recombinant proteins(Yang et al.2020),and inactivated SARS-CoV-2(Zhang et al.2021).

关键词： respiratory acute

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：