检索结果-内蒙古大学图书馆

25th International Joint Conference on Artificial intelligence, IJCAI 2016

作者： Liang, Jian He, Ran Sun, Zhenan Tan, Tieniu China Center for Research on Intelligent Perception and Computing CASIA China Center for Excellence in Brain Science and Intelligence Technology CAS China

Cross-modal learning tries to find various types of heterogeneous data (e.g., image) from a given query (e.g., text). Most cross-modal algorithms heavily rely on semantic labels and benefit from a semantic-preserving aggregation of pairs of heterogeneous data. However, the semantic labels are not readily obtained in many real-world applications. This paper studies the aggregation of these pairs unsupervisedly. Apart from lower pairwise correspondences that force the data from one pair to be close to each other, we propose a novel concept, referred as groupwise correspondences, supposing that each paired heterogeneous data are from an identical latent group. We incorporate this groupwise correspondences into canonical correlation analysis (CCA) model, and seek a latent common subspace where data are naturally clustered into several latent groups. To simplify this nonconvex and nonsmooth problem, we introduce a nonnegative orthogonal variable to represent the soft group membership, then two coupled computationally efficient subproblems (a generalized ratio-trace problem and a non-negative problem) are alternatively minimized to guarantee the proposed algorithm converges locally. Experimental results on two benchmark datasets demonstrate that the proposed unsupervised algorithm even achieves comparable performance to some state-of-the-art supervised cross-modal algorithms.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

How early language experience shapes the language-ready brain function and anatomy

How early language experience shapes the language-ready brai...

引用

第六届心理健康学术年会

作者： Yanyan Li Danling Peng Guosheng Ding Liang Wang CAS Key Laboratory of Mental Health Institute of Psychology Beijing 100101 China Department of Psychology University of Chinese Academy of Sciences State Key Laboratory of Cognitive Neuroscience and Learning & IDG/McGovern Institute for Brain Research Beijing Normal University CAS Key Laboratory of Mental Health Institute of Psychology CAS Center for Excellence in Brain Science and Intelligence Technology (CEBSIT)

One of the most important but challenging questions in neuroscience is how early language experience affects the language-ready brain function and anatomy, i.e., the development of dorsal and ventral streams in the left-hemisphere language network, as spoken language is ubiquitous in the environment of hearing infants. Congenitally profoundly deaf children born into hearing parents often do not receive functional language input until they receive special services or interact with other deaf individuals who use sign language. This presents a unique opportunity to explore how early language experience changes the language-ready brains becoming language-using brains. Here we recruited and compared functional and structural brain data from the following three groups:(1)congenitally profoundly deaf adults(n=31) with rare early sign language experience(congenitally deaf non-native signers, CDNN);(2) congenitally profoundly deaf adults(n=29) who were native signers of Chinese Sign Language(congenitally deaf native signers, CDN);(3) hearing speakers(HS)(n=31). Without early language input, compared with CDN and HS, CDNN has changed functional connectivity strength(FCS), that is, decreased FCS in left inferior frontal gyrus(Broca's area) but increased FCS in left angular gyrus(Geschwind'sarea), in the dorsal pathway, but not in the ventral pathway. Furthermore, when performing a passive sign language comprehension task, CDNN also activated less in dorsal part of left inferior frontal gyrus compared with CDN and HS. More important, CDN showed similar FCS and activation pattern as HS, suggesting general modality-independence of the core language network plasticity in the dorsal pathway might be affected purely by early language experience. We further find the part of superior longitudinal/arcuate fasciculus(SLF/AF) in posterior superior temporal gyrus(Wernicke's area)showed significantly enhanced fractional anisotropy(FA) in CDNN compared to CDN and HS,providing a possible str

关键词： Broca's area Wernicke's area Geschwind's area language dorsal and ventral pathways sensitive period

来源：评论

学校读者我要写书评

暂无评论

Distributed neural activities during multi-object working memory

Distributed neural activities during multi-object working me...

引用

中国神经科学学会第十二届全国学术会议

作者： Ya-Li PAN Wen-Jing ZHOU Yun-Lin LI Lian-Kun REN Liang WANG CAS Key Laboratory of Mental Health Institute of Psychology Department of Psychology University of Chinese Academy of Sciences Epilepsy Center of Yuquan Hospital Tsinghua University Capital Institute of Pediatrics Beijing Institute of Functional Neurosurgery Xuanwu Hospital Capital Medical University CAS Center for Excellence in Brain Science and Intelligence Technology

Objective: Working memory(WM) is responsible for temporarily holding information available for processing. However, it is still unclear how the brain represents multiple objects presented simultaneously. The current study is to explore the underlying neural mechanisms of maintaining visual objects. Methods: We developed a novel visuospatial delayed match to sample task with three types of memory load, while controlling the effect of perceptual load. Scalp EEG and intracranial EEG recorded from refractory epileptic patients were used to investigate maintenance-related neural activity. Results: Behavior performance deteriorated severely with increasing memory load. The memory capacity estimated by Cowan's K value first increased and then saturated at the load of 2, which was in consistence with the view that visual working memory was severely limited. Event related potentials(ERPs) analysis validated the effectiveness of controlling perceptual load. No load effect was observed during the first 320 ms perceptual period after sample onset, which contained the evoked response components P1 and N1. For the recorded local field potentials(LFPs), time-frequency decomposition was performed for each channel. We found that high-gamma activation increased mainly in frontal, parietal and lateral occipital cortex, indicating a distributed working memory circuit. Moreover, high-gamma activity did not increase monotonically with memory load increasing, implying a sensible neural basis of the limited memory capacity. In addition, compared with baseline activity, there were significantly increased neural activities during the delay period, even though cognitive load exceeded the capacity(i.e. at the load 4). Conclusion: this study may provide neural evidence for resource model of working memory, rather than the classical slot model.

关键词： Working memory capacity intracranial EEG high gamma resource model

来源：评论

学校读者我要写书评

暂无评论

Implementation of EEG emotion recognition system based on hierarchical convolutional neural networks 1

引用

8th International Conference on brain Inspired Cognitive Systems, BICS 2016

作者： Li, Jinpeng Zhang, Zhaoxiang He, Huiguang Research Center for Brain-Inspired Intelligence Institute of Automation Chinese Academy of Sciences Beijing China Beijing China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Beijing China

ISBN: (数字)9783319496856

ISBN: (纸本)9783319496849

Deep Learning (DL) is capable of excavating features hidden deep in complex data. In this paper, we introduce hierarchical convolutional neural networks (HCNN) to implement the EEG-based emotion classifier (positive, negative and neutral) in a movie-watching task. Differential Entropy (DE) is calculated as features at certain time interval for each channel. We organize features from different channels into two dimensional maps to train HCNN classifier. This approach extracts features contained in the spatial topology of electrodes directly, which is often neglected by the widely-used one-dimensional models. The performance of HCNN was compared with one-dimensional deep model SAE (Stacked Autoencoder), as well as traditional shallow models SVM and KNN. We find that HCNN (88.2% ± 3.5%) is better than SAE (85.4% ± 8.1%), and deep models are more favorable in emotion recognition BCI (brain-computer Interface) system than shallow models. Moreover, we show that models learned on one person is hard to transfer to others and the individual difference in EEG emotion-related signal is significant among peoples. Finally, we find Beta and Gamma (rather than Delta, Theta and Alpha) waves play the key role in emotion recognition. © Springer International Publishing AG 2016.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

An end-to-end Chinese discourse parser with adaptation to explicit and non-explicit relation recognition 20

An end-to-end Chinese discourse parser with adaptation to ex...

引用

20th SIGNLL Conference on Computational Natural Language Learning: Shared Task, CoNLL 2016

作者： Kang, Xiaomian Li, Haoran Zhou, Long Zhang, Jiajun Zong, Chengqing National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China CAS Center for Excellence in Brain Science and Intelligence Technology China

ISBN: (纸本)1932432663

This paper describes our end-to-end discourse parser in the CoNLL-2016 Shared Task on Chinese Shallow Discourse Parsing. To adapt to the characteristics of Chinese, we implement a uniform framework for both explicit and non-explicit relation parsing. In this framework, we are the first to utilize a seed-expansion approach for the argument extraction subtask. In the official evaluation, our system achieves an F1 score of 26.90% in overall performance on the blind test set. © 2016 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

引用

Journal of Genetics and Genomics 2017年第1期44卷 63-66页

作者： BO Yuan Tian-lin Cheng Kan Yang Xu Zhang Zilong Qiu Institute of Neuroscience Key Laboratory of Primate Neurobiology CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai Institutes for Biological Sciences Chinese Academy of Sciences Shanghai 200031 China Institute of Chemistry and Bioengineering Donghua University Shanghai 200051 China Shanghai Clinical Research Center Shanghai Institutes for Biological Sciences Chinese Academy of Sciences Shanghai 200031 China

Methyl-CpG binding protein 2 （MeCP2） has a crucial role in transcriptional regulation and neural development （Ausi6 et al., 2014）. Loss of function mutations of MECP2 in human lead to Rett syndrome （RTT）, a severe neurodevelopmental disorders （Amir et al., 1999）, whereas individuals with the chromosomal duplications containing the MECP2 locus showed severe autism-like symptoms （Ramocki et al., 2009）.

关键词： FGF Autism-related protein MeCP2 regulates FGF13 expression and emotional behaviors microRNAs

来源：评论

学校读者我要写书评

暂无评论

Towards robot self-consciousness (I): brain-inspired robot mirror neuron system model and its application in mirror self-recognition 1

引用

8th International Conference on brain Inspired Cognitive Systems, BICS 2016

作者： Zeng, Yi Zhao, Yuxuan Bai, Jun Institute of Automation Chinese Academy of Sciences Beijing China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai China

ISBN: (数字)9783319496856

ISBN: (纸本)9783319496849

Mirror Self-Recognition is a well accepted test to identify whether an animal is with self-consciousness. Mirror neuron system is believed to be one of the most important biological foundation for Mirror Self-Recognition. Inspired by the biological mirror neuron system of the mammalian brain, we propose a brain-inspired Robot Mirror Neuron System Model (Robot-MNS-Model) and we apply it to humanoid robots for mirror self-recognition. This model evaluates the similarity between the actual movements of robots and their visual perceptions. The association for self-recognition is supported by STDP learning which connects the correlated visual perception and motor control. The model is evaluated on self-recognition mirror test for 3 humanoid robots. Each robot has to decide which one is itself after a series of random movements facing a mirror. The results show that with the proposed model, multiple robots can pass the self-recognition mirror test at the same time, which is a step forward towards robot self-consciousness. © Springer International Publishing AG 2016.

关键词： Mirrors

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised multimodal deep learning for RGB-D object recognition 25

Semi-supervised multimodal deep learning for RGB-D object re...

引用

25th International Joint Conference on Artificial intelligence, IJCAI 2016

作者： Cheng, Yanhua Zhao, Xin Cai, Rui Li, Zhiwei Huang, Kaiqi Rui, Yong CRIPACandNLPR CASIA United States Microsoft Research United States CAS Center for Excellence in Brain Science and Intelligence Technology China

This paper studies the problem of RGB-D object recognition. Inspired by the great success of deep convolutional neural networks (DCNN) in AI, researchers have tried to apply it to improve the performance of RGB-D object recognition. However, DCNN always requires a large-scale annotated dataset to supervise its training. Manually labeling such a large RGB-D dataset is expensive and time consuming, which prevents DCNN from quickly promoting this research area. To address this problem, we propose a semi-supervised multimodal deep learning framework to train DCNN effectively based on very limited labeled data and massive unlabeled data. The core of our framework is a novel diversity preserving co-training algorithm, which can successfully guide DCNN to learn from the unlabeled RGB-D data by making full use of the complementary cues of the RGB and depth data in object representation. Experiments on the benchmark RGB-D dataset demonstrate that, with only 5% labeled training data, our approach achieves competitive performance for object recognition compared with those state-of-the-art results reported by fully-supervised methods.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Towards neural machine translation with partially aligned corpora

arXiv

引用

arXiv 2017年

作者： Wang, Yining Zhao, Yang Zhang, Jiajun Zong, Chengqing Xue, Zhengshan National Laboratory of Pattern Recognition CASIA Beijing China University of Chinese Academy of Sciences Beijing China CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai China Co. Ltd

While neural machine translation (NMT) has become the new paradigm, the parameter optimization requires large-scale parallel data which is scarce in many domains and language pairs. In this paper, we address a new translation scenario in which there only exists monolingual corpora and phrase pairs. We propose a new method towards translation with partially aligned sentence pairs which are derived from the phrase pairs and monolingual corpora. To make full use of the partially aligned corpora, we adapt the conventional NMT training method in two aspects. On one hand, different generation strategies are designed for aligned and unaligned target words. On the other hand, a different objective function is designed to model the partially aligned parts. The experiments demonstrate that our method can achieve a relatively good result in such a translation scenario, and tiny bitexts can boost translation quality to a large extent. Copyright © 2017, The Authors. All rights reserved.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

An improved recurrent network for online equality-constrained quadratic programming 1

引用

8th International Conference on brain Inspired Cognitive Systems, BICS 2016

作者： Chen, Ke Zhang, Zhaoxiang Department of Signal Processing Tampere University of Technology Tampere Finland CAS Center for Excellence in Brain Science and Intelligence Technology CASIA Beijing China

ISBN: (数字)9783319496856

ISBN: (纸本)9783319496849

Encouraged by the success of conventional GradientNet and recently-proposed ZhangNet for online equality-constrained quadratic programming problem, an improved recurrent network and its electronic implementation are firstly proposed and developed in this paper. Exploited in the primal form of quadratic programming with linear equality constraints, the proposed neural model can solve the problem effectively. Moreover, compared to the existing recurrent networks, i.e., GradientNet (GN) and ZhangNet (ZN), our model can theoretically guarantee superior global exponential convergence performance. Robustness performance of our such neural model is also analysed under a large model implementation error, with the upper bound of stead-state solution error estimated. Simulation results demonstrate theoretical analysis on the proposed model for online equality-constrained quadratic programming. © Springer International Publishing AG 2016.

关键词： Quadratic programming

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：