检索结果-内蒙古大学图书馆

Individual Alpha Frequency tACS modifies the detection of space-time optical illusion

学校读者我要写书评

暂无评论

Brain Stimulation 2025年第1期18卷 360-360页

作者： Scoccia, Adriano Neri, Francesco Catrambone, Vincenzo Cinti, Alessandra Benelli, Alberto Romanella, Sara Grabot, Laetitia Valenza, Gaetano Smeralda, Carmelo Luca Santarnecchi, Emiliano van Wassenhove, Virginie Rossi, Simone Siena Brain Investigation and Neuromodulation Lab (Si-BIN Lab) Department of Medicine Surgery and Neuroscience Neurology and Clinical Neurophysiology Section University of Siena Italy Oto-Neuro-Tech Conjoined Lab Policlinico Le Scotte University of Siena Italy Department of Information Engineering University of Pisa Bioengineering & Robotics Research Center “E. Piaggio” Pisa Italy Precision Neuroscience & Neuromodulation Program Massachusetts General Hospital Harvard Medical School Boston MA USA Cognitive Neuroimaging Unit CEA DRF/Joliot NeuroSpin INSERM Université Paris-Saclay 91191 Gif-sur-Yvette France Department for Cognitive Neuroscience Faculty of Biology & Cognitive Interaction Technology Center of Excellence Bielefeld University Bielefeld Germany

Neuro-adaptive tracking control for uncertain Euler-Lagrange systems with time-varying output constraints and obstacle avoidance

学校读者我要写书评

暂无评论

Neuro-adaptive tracking control for uncertain Euler-Lagrange...

第三十九届中国控制会议

作者： Zhi-Gang Zhou Xinwei Chen Ruifeng Li Xiao-Ning Shi Kuanchang Wen School of Electronic Information Jiangsu University of Science and Technology Industrial Robot Application of Fujian University Engineering Research Center Minjiang University The State Key Lab of Robotics and Systems Harbin Institute of Technology

This paper addresses the tracking control problem for uncertain Euler-Lagrange system with time-varying output constraints in an environment containing obstacles. First, a novel log-type attractive potential field is utilized to describe the trajectory tracking task with time-varying constraints, and a bounded artificial potential field is established to describe the obstacle avoidance task. Then, by incorporating the two artificial potential fields(APFs) into the dynamic surface control, a neuro-adaptive tracking control is designed for the uncertain Euler-Lagrange system, which can ensure the system to fulfill the trajectory track task within time-varying limit range while avoiding obstacles. Because the obstacle avoidance task has a higher priority, the proposed control scheme can also guarantee the obstacle avoiding task can be fulfilled first when it is conflicted with the trajectory tracking task. Numerical simulations are provided to demonstrate the efficacy of the control strategy.

关键词： Uncertain Euler-Lagrange System Tracking Control Obstacle Avoidance Artificial Potential Field Dynamic Surface Control Neuro-adaptive Control

Prescribed Performance Attitude Tracking Control for Spacecraft under Multi-Constraint

学校读者我要写书评

暂无评论

Prescribed Performance Attitude Tracking Control for Spacecr...

第三十九届中国控制会议

作者： Xiao-Ning Shi Weixin Chen Ruifeng Li Zhi-Gang Zhou Kuanchang Wen School of Electronic Information Jiangsu University of Science and Technology Industrial Robot Application of Fujian University Engineering Research Center Minjiang University The State Key Lab of Robotics and Systems Harbin Institute of Technology

This paper investigates the prescribed performance attitude tracking problem for the rigid spacecraft subject to external disturbances and multiple constraints, including input saturation and full-state constraints. By employing the barrier Lyapunov function and an error-shifting transformation, a fixed-time tracking control strategy is devised capable of dealing with the prescribed performance problem under a completely unknown initial tracking condition. In addition, an auxiliary system is also introduced to compensate the adverse effect arising from the input saturation. Finally, the performance of the proposed control schemes is demonstrated by numerical simulations.

关键词： Attitude tracking Prescribed performance BLF Fixed-time control Input saturation

Future Vector Enhanced LSTM Language Model for LVCSR

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Qi Qian, Yanmin Yu, Kai Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering SpeechLab Department of Computer Science and Engineering Brain Science and Technology Research Center Shanghai Jiao Tong University Shanghai China

Language models (LM) play an important role in large vocabulary continuous speech recognition (LVCSR). However, traditional language models only predict next single word with given history, while the consecutive predictions on a sequence of words are usually demanded and useful in LVCSR. The mismatch between the single word prediction modeling in trained and the long term sequence prediction in read demands may lead to the performance degradation. In this paper, a novel enhanced long short-term memory (LSTM) LM using the future vector is proposed. In addition to the given history, the rest of the sequence will be also embedded by future vectors. This future vector can be incorporated with the LSTM LM, so it has the ability to model much longer term sequence level information. Experiments show that, the proposed new LSTM LM gets a better result on BLEU scores for long term sequence prediction. For the speech recognition rescoring, although the proposed LSTM LM obtains very slight gains, the new model seems obtain the great complementary with the conventional LSTM LM. Rescoring using both the new and conventional LSTM LMs can achieve a very large improvement on the word error rate. Copyright © 2020, The Authors. All rights reserved.

关键词： Long short-term memory

Mean phase coherence modified for piecewise constant phase difference data 3

学校读者我要写书评

暂无评论

Mean phase coherence modified for piecewise constant phase d...

3rd School on Dynamics of Complex Networks and their Application in Intellectual robotics, DCNAIR 2019

作者： Khorev, Vladimir Department of Dynamic Modeling and Biomedical Engineering Saratov State University Saratov Russia Neuroscience and Cognitive Technology Lab Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia

We propose a modification of the mean phase coherence method based on the statistics arrange of phase difference data. The modification aimed towards better analysis of data of coupled oscillators under influence of s... 详细信息

ISBN: (纸本)9781728124704

关键词： Synchronization Coherence Oscillators Couplings Indexes Time series analysis Delays

Topological Higher-Order Neuron Model Based on Homology-Continuity Principle 2

学校读者我要写书评

暂无评论

Topological Higher-Order Neuron Model Based on Homology-Cont...

2nd China Symposium on cognitive Computing and Hybrid Intelligence, CCHI 2019

作者： Ning, Xin Li, Weijun Tian, Weijuan Lu, Yueyue Institute of Semiconductors Wave Joint Lab of Cognitive Computing Technology Chinese Academy of Sciences Center of Materials Science and Optoelectronics Engineering School of Microelectronics University of Chinese Academy of Sciences Beijing100083 China

ISBN: (纸本)9781728140919

Recently, deep neural networks (DNNs) have been applied in various areas in computer vision. However, due to the simple neuron configuration, the existing DNNs rely heavily on the diversity of the data distribution and have poor generalization performance. In addition, the excessive network complexity also leads to low learning efficiency. To solve above problems, a topological higher-order neuron model was proposed, which is modeled according to the point-set topology in high-dimensional space. The proposed neuron is determined by the adaptively changed center and the direction weights with strong generalization ability. The high-dimensional feature space of the samples is constructed by a category-based covering learning method, thus achieving an optimal coverage of each category. Experiments on several different classical datasets demonstrate the generalization of the proposed neuron model, which provides a new approach for the further development of DNNs and can be widely used in computer vision. © 2019 IEEE.

关键词： Deep neural networks

Structured hierarchical dialogue policy with graph neural networks

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Chen, Zhi Liu, Xiaoyuan Chen, Lu Yu, Kai Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Eng. SpeechLab Department of Computer Science and Engineering Brain Science and Technology Research Center Shanghai Jiao Tong University Shanghai China

Dialogue policy training for composite tasks, such as restaurant reservation in multiple places, is a practically important and challenging problem. Recently, hierarchical deep reinforcement learning (HDRL) methods have achieved good performance in composite tasks. However, in vanilla HDRL, both top-level and low-level policies are all represented by multi-layer perceptrons (MLPs) which take the concatenation of all observations from the environment as the input for predicting actions. Thus, traditional HDRL approach often suffers from low sampling efficiency and poor transferability. In this paper, we address these problems by utilizing the flexibility of graph neural networks (GNNs). A novel ComNet is proposed to model the structure of a hierarchical agent. The performance of ComNet is tested on composited tasks of the PyDial benchmark. Experiments show that ComNet outperforms vanilla HDRL systems with performance close to the upper bound. It not only achieves sample efficiency but also is more robust to noise while maintaining the transferability to other composite tasks. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep learning

Dual learning for dialogue state tracking

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Chen, Zhi Chen, Lu Zhao, Yanbin Zhu, Su Yu, Kai Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Eng. SpeechLab Department of Computer Science and Engineering Brain Science and Technology Research Center Shanghai Jiao Tong University Shanghai China

In task-oriented multi-turn dialogue systems, dialogue state refers to a compact representation of the user goal in the context of dialogue history. Dialogue state tracking (DST) is to estimate the dialogue state at each turn. Due to the dependency on complicated dialogue history contexts, DST data annotation is more expensive than single-sentence language understanding, which makes the task more challenging. In this work, we formulate DST as a sequence generation problem and propose a novel dual-learning framework to make full use of unlabeled data. In the dual-learning framework, there are two agents: the primal tracker agent (utterance-to-state generator) and the dual utterance generator agent (state-to-utterance generator). Compared with traditional supervised learning framework, dual learning can iteratively update both agents through the reconstruction error and reward signal respectively without labeled data. Reward sparsity problem is hard to solve in previous DST methods. In this work, the reformulation of DST as a sequence generation model effectively alleviates this problem. We call this primal tracker agent dual-DST. Experimental results on MultiWOZ2.1 dataset show that the proposed dual-DST works very well, especially when labelled data is limited. It achieves comparable performance to the system where labeled data is fully used. Copyright © 2020, The Authors. All rights reserved.

关键词： Iterative methods

CREDIT: Coarse-to-fine Sequence generation for dialogue state tracking

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Chen, Zhi Chen, Lu Xu, Zihan Zhao, Yanbin Zhu, Su Yu, Kai Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Eng. SpeechLab Department of Computer Science and Engineering Brain Science and Technology Research Center Shanghai Jiao Tong University Shanghai China

In dialogue systems, a dialogue state tracker aims to accurately find a compact representation of the current dialogue status, based on the entire dialogue history. While previous approaches often define dialogue states as a combination of separate triples (domain-slot-value), in this paper, we employ a structured state representation and cast dialogue state tracking as a sequence generation problem. Based on this new formulation, we propose a CoaRsE-to-fine DIalogue state Tracking (CREDIT) approach. Taking advantage of the structured state representation, which is a marked language sequence, we can further fine-tune the pre-trained model (by supervised learning) by optimizing natural language metrics with the policy gradient method. Like all generative state tracking methods, CREDIT does not rely on pre-defined dialogue ontology enumerating all possible slot values. Experiments demonstrate our tracker achieves encouraging joint goal accuracy for the five domains in MultiWOZ 2.0 and MultiWOZ 2.1 datasets. Copyright © 2020, The Authors. All rights reserved.

关键词： Machine learning